diff --git "a/checkpoint-1831670/trainer_state.json" "b/checkpoint-1831670/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1831670/trainer_state.json" @@ -0,0 +1,21679 @@ +{ + "best_metric": 3.837454080581665, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/full/transformer/2/checkpoints/checkpoint-839510", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 1831670, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.8802, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8386, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1899, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9736, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8162, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.6929, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5896, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5229, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4698, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3891, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3507, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3099, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.2682, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.204, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1785, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1472, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1075, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0742, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0523, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0271, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 4.997, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9696, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9579, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9284, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9183, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8916, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8804, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773644932430885e-05, + "loss": 4.8625, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765258984920364e-05, + "loss": 4.829, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8316, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8018, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7909, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7798, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 4.7727, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 4.7487, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7381, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7384, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.7207, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 4.7124, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.694, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6774, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.671, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6494, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6669, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.6405, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6414, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6314, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6274, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.9597605549924894e-05, + "loss": 4.6176, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.595, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.5874, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.579, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5857, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5648, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.575, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5484, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.542, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5385, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 4.534, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.95053765061129e-05, + "loss": 4.5284, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5135, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5092, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 4.5172, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 4.4978, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.493, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.4931, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.4902, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 4.4708, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4816, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4704, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 4.4611, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404794272397856e-05, + "loss": 4.466, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4527, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388055134984274e-05, + "loss": 4.4653, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.465, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4557, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4392, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4274, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4179, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.4323, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4311, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4279, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4028, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.4013, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.4074, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.3946, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.3992, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.3967, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3966, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925391273242342e-05, + "loss": 4.3855, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3832, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3713, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3851, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3688, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3559, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3611, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3742, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3663, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3627, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3425, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3593, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3328, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3493, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3546, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912818903498054e-05, + "loss": 4.3388, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911980308747002e-05, + "loss": 4.3313, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3071, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3219, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3216, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3185, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3224, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3049, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3078, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3145, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.317, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3038, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.3019, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.2976, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.298, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.302, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994063011223415e-05, + "loss": 4.289, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985677063712895e-05, + "loss": 4.2839, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977291116202375e-05, + "loss": 4.2821, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.2773, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.2832, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2815, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2873, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.2627, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2759, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2793, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.2664, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2823, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2642, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2763, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.2672, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.246, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.2461, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.249, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2571, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2582, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2573, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.2476, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88096376812069e-05, + "loss": 4.2422, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880125173369638e-05, + "loss": 4.2368, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.233, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.2404, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.2495, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876774070126176e-05, + "loss": 4.2429, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875935475375124e-05, + "loss": 4.2247, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875096880624072e-05, + "loss": 4.2266, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.19438362121582, + "eval_runtime": 555.8109, + "eval_samples_per_second": 686.548, + "eval_steps_per_second": 21.455, + "step": 76319 + }, + { + "epoch": 0.0, + "learning_rate": 4.87425828587302e-05, + "loss": 4.2289, + "step": 76800 + }, + { + "epoch": 0.0, + "learning_rate": 4.873419691121968e-05, + "loss": 4.2236, + "step": 77312 + }, + { + "epoch": 0.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.2185, + "step": 77824 + }, + { + "epoch": 0.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2184, + "step": 78336 + }, + { + "epoch": 0.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.2099, + "step": 78848 + }, + { + "epoch": 0.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.1937, + "step": 79360 + }, + { + "epoch": 0.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.2023, + "step": 79872 + }, + { + "epoch": 0.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.2132, + "step": 80384 + }, + { + "epoch": 0.0, + "learning_rate": 4.867549527864604e-05, + "loss": 4.2027, + "step": 80896 + }, + { + "epoch": 0.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.2038, + "step": 81408 + }, + { + "epoch": 0.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.2079, + "step": 81920 + }, + { + "epoch": 0.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.2061, + "step": 82432 + }, + { + "epoch": 0.0, + "learning_rate": 4.864196786740769e-05, + "loss": 4.1955, + "step": 82944 + }, + { + "epoch": 0.0, + "learning_rate": 4.863358191989717e-05, + "loss": 4.198, + "step": 83456 + }, + { + "epoch": 0.0, + "learning_rate": 4.862519597238665e-05, + "loss": 4.1913, + "step": 83968 + }, + { + "epoch": 0.0, + "learning_rate": 4.861681002487613e-05, + "loss": 4.1783, + "step": 84480 + }, + { + "epoch": 0.0, + "learning_rate": 4.860842407736561e-05, + "loss": 4.1873, + "step": 84992 + }, + { + "epoch": 0.0, + "learning_rate": 4.860003812985509e-05, + "loss": 4.1906, + "step": 85504 + }, + { + "epoch": 0.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.1885, + "step": 86016 + }, + { + "epoch": 0.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.1914, + "step": 86528 + }, + { + "epoch": 0.0, + "learning_rate": 4.857489666612726e-05, + "loss": 4.1762, + "step": 87040 + }, + { + "epoch": 0.0, + "learning_rate": 4.856651071861674e-05, + "loss": 4.1871, + "step": 87552 + }, + { + "epoch": 0.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.1748, + "step": 88064 + }, + { + "epoch": 0.0, + "learning_rate": 4.8549755202399435e-05, + "loss": 4.1841, + "step": 88576 + }, + { + "epoch": 0.0, + "learning_rate": 4.8541369254888915e-05, + "loss": 4.1737, + "step": 89088 + }, + { + "epoch": 0.0, + "learning_rate": 4.8532983307378395e-05, + "loss": 4.1726, + "step": 89600 + }, + { + "epoch": 0.0, + "learning_rate": 4.8524597359867875e-05, + "loss": 4.1786, + "step": 90112 + }, + { + "epoch": 0.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.1586, + "step": 90624 + }, + { + "epoch": 0.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.1743, + "step": 91136 + }, + { + "epoch": 0.01, + "learning_rate": 4.8499455896140044e-05, + "loss": 4.1566, + "step": 91648 + }, + { + "epoch": 0.01, + "learning_rate": 4.8491069948629524e-05, + "loss": 4.1623, + "step": 92160 + }, + { + "epoch": 0.01, + "learning_rate": 4.8482684001119e-05, + "loss": 4.1624, + "step": 92672 + }, + { + "epoch": 0.01, + "learning_rate": 4.847431443241221e-05, + "loss": 4.1677, + "step": 93184 + }, + { + "epoch": 0.01, + "learning_rate": 4.846592848490169e-05, + "loss": 4.1561, + "step": 93696 + }, + { + "epoch": 0.01, + "learning_rate": 4.845754253739117e-05, + "loss": 4.1524, + "step": 94208 + }, + { + "epoch": 0.01, + "learning_rate": 4.844915658988065e-05, + "loss": 4.1646, + "step": 94720 + }, + { + "epoch": 0.01, + "learning_rate": 4.844078702117387e-05, + "loss": 4.1549, + "step": 95232 + }, + { + "epoch": 0.01, + "learning_rate": 4.843240107366335e-05, + "loss": 4.1622, + "step": 95744 + }, + { + "epoch": 0.01, + "learning_rate": 4.842401512615282e-05, + "loss": 4.1461, + "step": 96256 + }, + { + "epoch": 0.01, + "learning_rate": 4.84156291786423e-05, + "loss": 4.1366, + "step": 96768 + }, + { + "epoch": 0.01, + "learning_rate": 4.840724323113178e-05, + "loss": 4.1409, + "step": 97280 + }, + { + "epoch": 0.01, + "learning_rate": 4.8398873662425e-05, + "loss": 4.1353, + "step": 97792 + }, + { + "epoch": 0.01, + "learning_rate": 4.839048771491447e-05, + "loss": 4.1502, + "step": 98304 + }, + { + "epoch": 0.01, + "learning_rate": 4.838210176740395e-05, + "loss": 4.1387, + "step": 98816 + }, + { + "epoch": 0.01, + "learning_rate": 4.837371581989343e-05, + "loss": 4.1446, + "step": 99328 + }, + { + "epoch": 0.01, + "learning_rate": 4.836532987238292e-05, + "loss": 4.1385, + "step": 99840 + }, + { + "epoch": 0.01, + "learning_rate": 4.8356960303676126e-05, + "loss": 4.1434, + "step": 100352 + }, + { + "epoch": 0.01, + "learning_rate": 4.8348574356165606e-05, + "loss": 4.1408, + "step": 100864 + }, + { + "epoch": 0.01, + "learning_rate": 4.8340188408655086e-05, + "loss": 4.1193, + "step": 101376 + }, + { + "epoch": 0.01, + "learning_rate": 4.8331802461144566e-05, + "loss": 4.1266, + "step": 101888 + }, + { + "epoch": 0.01, + "learning_rate": 4.8323432892437775e-05, + "loss": 4.1202, + "step": 102400 + }, + { + "epoch": 0.01, + "learning_rate": 4.8315046944927255e-05, + "loss": 4.1372, + "step": 102912 + }, + { + "epoch": 0.01, + "learning_rate": 4.8306660997416735e-05, + "loss": 4.1137, + "step": 103424 + }, + { + "epoch": 0.01, + "learning_rate": 4.8298291428709944e-05, + "loss": 4.1378, + "step": 103936 + }, + { + "epoch": 0.01, + "learning_rate": 4.8289905481199424e-05, + "loss": 4.1112, + "step": 104448 + }, + { + "epoch": 0.01, + "learning_rate": 4.8281519533688904e-05, + "loss": 4.112, + "step": 104960 + }, + { + "epoch": 0.01, + "learning_rate": 4.8273133586178384e-05, + "loss": 4.1203, + "step": 105472 + }, + { + "epoch": 0.01, + "learning_rate": 4.826474763866787e-05, + "loss": 4.1134, + "step": 105984 + }, + { + "epoch": 0.01, + "learning_rate": 4.825637806996108e-05, + "loss": 4.1133, + "step": 106496 + }, + { + "epoch": 0.01, + "learning_rate": 4.824799212245056e-05, + "loss": 4.1069, + "step": 107008 + }, + { + "epoch": 0.01, + "learning_rate": 4.823960617494004e-05, + "loss": 4.1027, + "step": 107520 + }, + { + "epoch": 0.01, + "learning_rate": 4.823122022742952e-05, + "loss": 4.1166, + "step": 108032 + }, + { + "epoch": 0.01, + "learning_rate": 4.822285065872273e-05, + "loss": 4.1045, + "step": 108544 + }, + { + "epoch": 0.01, + "learning_rate": 4.821446471121221e-05, + "loss": 4.1043, + "step": 109056 + }, + { + "epoch": 0.01, + "learning_rate": 4.820607876370169e-05, + "loss": 4.1051, + "step": 109568 + }, + { + "epoch": 0.01, + "learning_rate": 4.819769281619117e-05, + "loss": 4.1085, + "step": 110080 + }, + { + "epoch": 0.01, + "learning_rate": 4.818930686868065e-05, + "loss": 4.0893, + "step": 110592 + }, + { + "epoch": 0.01, + "learning_rate": 4.818093729997386e-05, + "loss": 4.1085, + "step": 111104 + }, + { + "epoch": 0.01, + "learning_rate": 4.817255135246334e-05, + "loss": 4.0956, + "step": 111616 + }, + { + "epoch": 0.01, + "learning_rate": 4.816416540495282e-05, + "loss": 4.0981, + "step": 112128 + }, + { + "epoch": 0.01, + "learning_rate": 4.8155779457442305e-05, + "loss": 4.1036, + "step": 112640 + }, + { + "epoch": 0.01, + "learning_rate": 4.8147409888735514e-05, + "loss": 4.0928, + "step": 113152 + }, + { + "epoch": 0.01, + "learning_rate": 4.8139023941224994e-05, + "loss": 4.1108, + "step": 113664 + }, + { + "epoch": 0.01, + "learning_rate": 4.8130637993714474e-05, + "loss": 4.1141, + "step": 114176 + }, + { + "epoch": 0.01, + "learning_rate": 4.8122252046203954e-05, + "loss": 4.1076, + "step": 114688 + }, + { + "epoch": 0.01, + "learning_rate": 4.811388247749716e-05, + "loss": 4.0925, + "step": 115200 + }, + { + "epoch": 0.01, + "learning_rate": 4.810549652998664e-05, + "loss": 4.0857, + "step": 115712 + }, + { + "epoch": 0.01, + "learning_rate": 4.809711058247612e-05, + "loss": 4.0814, + "step": 116224 + }, + { + "epoch": 0.01, + "learning_rate": 4.80887246349656e-05, + "loss": 4.0943, + "step": 116736 + }, + { + "epoch": 0.01, + "learning_rate": 4.808035506625881e-05, + "loss": 4.1051, + "step": 117248 + }, + { + "epoch": 0.01, + "learning_rate": 4.807196911874829e-05, + "loss": 4.0959, + "step": 117760 + }, + { + "epoch": 0.01, + "learning_rate": 4.806358317123777e-05, + "loss": 4.0805, + "step": 118272 + }, + { + "epoch": 0.01, + "learning_rate": 4.805519722372726e-05, + "loss": 4.0752, + "step": 118784 + }, + { + "epoch": 0.01, + "learning_rate": 4.804682765502047e-05, + "loss": 4.0855, + "step": 119296 + }, + { + "epoch": 0.01, + "learning_rate": 4.803844170750995e-05, + "loss": 4.0735, + "step": 119808 + }, + { + "epoch": 0.01, + "learning_rate": 4.803005575999943e-05, + "loss": 4.0806, + "step": 120320 + }, + { + "epoch": 0.01, + "learning_rate": 4.802166981248891e-05, + "loss": 4.0841, + "step": 120832 + }, + { + "epoch": 0.01, + "learning_rate": 4.8013300243782116e-05, + "loss": 4.0876, + "step": 121344 + }, + { + "epoch": 0.01, + "learning_rate": 4.8004914296271596e-05, + "loss": 4.0765, + "step": 121856 + }, + { + "epoch": 0.02, + "learning_rate": 4.7996528348761076e-05, + "loss": 4.0774, + "step": 122368 + }, + { + "epoch": 0.02, + "learning_rate": 4.7988142401250556e-05, + "loss": 4.0694, + "step": 122880 + }, + { + "epoch": 0.02, + "learning_rate": 4.7979772832543765e-05, + "loss": 4.0806, + "step": 123392 + }, + { + "epoch": 0.02, + "learning_rate": 4.7971386885033245e-05, + "loss": 4.079, + "step": 123904 + }, + { + "epoch": 0.02, + "learning_rate": 4.7963000937522725e-05, + "loss": 4.0566, + "step": 124416 + }, + { + "epoch": 0.02, + "learning_rate": 4.795461499001221e-05, + "loss": 4.0687, + "step": 124928 + }, + { + "epoch": 0.02, + "learning_rate": 4.794626180010915e-05, + "loss": 4.0795, + "step": 125440 + }, + { + "epoch": 0.02, + "learning_rate": 4.793787585259863e-05, + "loss": 4.0849, + "step": 125952 + }, + { + "epoch": 0.02, + "learning_rate": 4.792948990508811e-05, + "loss": 4.0738, + "step": 126464 + }, + { + "epoch": 0.02, + "learning_rate": 4.792110395757759e-05, + "loss": 4.0634, + "step": 126976 + }, + { + "epoch": 0.02, + "learning_rate": 4.791271801006707e-05, + "loss": 4.077, + "step": 127488 + }, + { + "epoch": 0.02, + "learning_rate": 4.790433206255655e-05, + "loss": 4.0552, + "step": 128000 + }, + { + "epoch": 0.02, + "learning_rate": 4.789594611504603e-05, + "loss": 4.0715, + "step": 128512 + }, + { + "epoch": 0.02, + "learning_rate": 4.788756016753551e-05, + "loss": 4.0768, + "step": 129024 + }, + { + "epoch": 0.02, + "learning_rate": 4.787919059882872e-05, + "loss": 4.0681, + "step": 129536 + }, + { + "epoch": 0.02, + "learning_rate": 4.78708046513182e-05, + "loss": 4.0658, + "step": 130048 + }, + { + "epoch": 0.02, + "learning_rate": 4.786241870380768e-05, + "loss": 4.045, + "step": 130560 + }, + { + "epoch": 0.02, + "learning_rate": 4.7854032756297166e-05, + "loss": 4.0477, + "step": 131072 + }, + { + "epoch": 0.02, + "learning_rate": 4.7845663187590375e-05, + "loss": 4.0551, + "step": 131584 + }, + { + "epoch": 0.02, + "learning_rate": 4.7837277240079855e-05, + "loss": 4.0569, + "step": 132096 + }, + { + "epoch": 0.02, + "learning_rate": 4.7828907671373064e-05, + "loss": 4.062, + "step": 132608 + }, + { + "epoch": 0.02, + "learning_rate": 4.7820521723862544e-05, + "loss": 4.0509, + "step": 133120 + }, + { + "epoch": 0.02, + "learning_rate": 4.7812135776352024e-05, + "loss": 4.0461, + "step": 133632 + }, + { + "epoch": 0.02, + "learning_rate": 4.7803749828841504e-05, + "loss": 4.0584, + "step": 134144 + }, + { + "epoch": 0.02, + "learning_rate": 4.7795363881330984e-05, + "loss": 4.0653, + "step": 134656 + }, + { + "epoch": 0.02, + "learning_rate": 4.7786977933820464e-05, + "loss": 4.0515, + "step": 135168 + }, + { + "epoch": 0.02, + "learning_rate": 4.7778591986309944e-05, + "loss": 4.0566, + "step": 135680 + }, + { + "epoch": 0.02, + "learning_rate": 4.7770206038799423e-05, + "loss": 4.048, + "step": 136192 + }, + { + "epoch": 0.02, + "learning_rate": 4.776183647009263e-05, + "loss": 4.0527, + "step": 136704 + }, + { + "epoch": 0.02, + "learning_rate": 4.775345052258212e-05, + "loss": 4.0562, + "step": 137216 + }, + { + "epoch": 0.02, + "learning_rate": 4.774508095387533e-05, + "loss": 4.0433, + "step": 137728 + }, + { + "epoch": 0.02, + "learning_rate": 4.773669500636481e-05, + "loss": 4.0419, + "step": 138240 + }, + { + "epoch": 0.02, + "learning_rate": 4.772830905885429e-05, + "loss": 4.0412, + "step": 138752 + }, + { + "epoch": 0.02, + "learning_rate": 4.771992311134377e-05, + "loss": 4.0387, + "step": 139264 + }, + { + "epoch": 0.02, + "learning_rate": 4.771153716383325e-05, + "loss": 4.0455, + "step": 139776 + }, + { + "epoch": 0.02, + "learning_rate": 4.770315121632272e-05, + "loss": 4.0465, + "step": 140288 + }, + { + "epoch": 0.02, + "learning_rate": 4.76947652688122e-05, + "loss": 4.0511, + "step": 140800 + }, + { + "epoch": 0.02, + "learning_rate": 4.768637932130168e-05, + "loss": 4.0327, + "step": 141312 + }, + { + "epoch": 0.02, + "learning_rate": 4.76780097525949e-05, + "loss": 4.0395, + "step": 141824 + }, + { + "epoch": 0.02, + "learning_rate": 4.766962380508437e-05, + "loss": 4.0535, + "step": 142336 + }, + { + "epoch": 0.02, + "learning_rate": 4.766123785757386e-05, + "loss": 4.0377, + "step": 142848 + }, + { + "epoch": 0.02, + "learning_rate": 4.765285191006334e-05, + "loss": 4.0518, + "step": 143360 + }, + { + "epoch": 0.02, + "learning_rate": 4.764448234135655e-05, + "loss": 4.0368, + "step": 143872 + }, + { + "epoch": 0.02, + "learning_rate": 4.7636096393846026e-05, + "loss": 4.0517, + "step": 144384 + }, + { + "epoch": 0.02, + "learning_rate": 4.7627710446335506e-05, + "loss": 4.0421, + "step": 144896 + }, + { + "epoch": 0.02, + "learning_rate": 4.7619324498824986e-05, + "loss": 4.0262, + "step": 145408 + }, + { + "epoch": 0.02, + "learning_rate": 4.7610954930118195e-05, + "loss": 4.0265, + "step": 145920 + }, + { + "epoch": 0.02, + "learning_rate": 4.7602568982607675e-05, + "loss": 4.03, + "step": 146432 + }, + { + "epoch": 0.02, + "learning_rate": 4.7594183035097155e-05, + "loss": 4.0425, + "step": 146944 + }, + { + "epoch": 0.02, + "learning_rate": 4.7585797087586635e-05, + "loss": 4.0371, + "step": 147456 + }, + { + "epoch": 0.02, + "learning_rate": 4.7577427518879844e-05, + "loss": 4.0413, + "step": 147968 + }, + { + "epoch": 0.02, + "learning_rate": 4.7569041571369324e-05, + "loss": 4.0332, + "step": 148480 + }, + { + "epoch": 0.02, + "learning_rate": 4.756065562385881e-05, + "loss": 4.0279, + "step": 148992 + }, + { + "epoch": 0.02, + "learning_rate": 4.755226967634829e-05, + "loss": 4.025, + "step": 149504 + }, + { + "epoch": 0.02, + "learning_rate": 4.75439001076415e-05, + "loss": 4.0208, + "step": 150016 + }, + { + "epoch": 0.02, + "learning_rate": 4.753551416013098e-05, + "loss": 4.029, + "step": 150528 + }, + { + "epoch": 0.02, + "learning_rate": 4.752712821262046e-05, + "loss": 4.0458, + "step": 151040 + }, + { + "epoch": 0.02, + "learning_rate": 4.751875864391367e-05, + "loss": 4.0294, + "step": 151552 + }, + { + "epoch": 0.02, + "learning_rate": 4.751037269640315e-05, + "loss": 4.0219, + "step": 152064 + }, + { + "epoch": 0.02, + "learning_rate": 4.750198674889263e-05, + "loss": 4.0224, + "step": 152576 + }, + { + "epoch": 0.03, + "eval_loss": 4.024528503417969, + "eval_runtime": 575.6455, + "eval_samples_per_second": 662.892, + "eval_steps_per_second": 20.716, + "step": 152638 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493617180185845e-05, + "loss": 4.0278, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748523123267532e-05, + "loss": 4.0254, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.74768452851648e-05, + "loss": 4.0161, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746845933765428e-05, + "loss": 4.0179, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460073390143764e-05, + "loss": 4.0169, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451687442633244e-05, + "loss": 3.9974, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443301495122724e-05, + "loss": 4.0081, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434915547612204e-05, + "loss": 4.0206, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426529600101684e-05, + "loss": 4.005, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741816003139489e-05, + "loss": 4.0117, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740977408388437e-05, + "loss": 4.0178, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740138813637385e-05, + "loss": 4.0155, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739300218886333e-05, + "loss": 4.0037, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738461624135281e-05, + "loss": 4.0107, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737623029384229e-05, + "loss": 4.0041, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736784434633177e-05, + "loss": 3.9963, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735945839882125e-05, + "loss": 4.002, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735108883011446e-05, + "loss": 4.0054, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734270288260394e-05, + "loss": 4.0079, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733431693509343e-05, + "loss": 4.0101, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732593098758291e-05, + "loss": 3.9978, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731756141887612e-05, + "loss": 4.0085, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.73091754713656e-05, + "loss": 3.9981, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730078952385508e-05, + "loss": 4.0041, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729240357634456e-05, + "loss": 3.9989, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728403400763777e-05, + "loss": 3.9968, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727564806012725e-05, + "loss": 4.0045, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726726211261673e-05, + "loss": 3.9857, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258892543909936e-05, + "loss": 3.9999, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250506596399416e-05, + "loss": 3.9876, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7242120648888896e-05, + "loss": 3.9903, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723373470137838e-05, + "loss": 3.9933, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225348753867856e-05, + "loss": 3.9969, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216962806357336e-05, + "loss": 3.9905, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208576858846816e-05, + "loss": 3.9832, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200190911336296e-05, + "loss": 3.999, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191821342629505e-05, + "loss": 3.9888, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183435395118985e-05, + "loss": 3.9988, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175049447608465e-05, + "loss": 3.9856, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166663500097945e-05, + "loss": 3.9713, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158293931391154e-05, + "loss": 3.9745, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149907983880634e-05, + "loss": 3.9778, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714152203637012e-05, + "loss": 3.9932, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713315246766333e-05, + "loss": 3.9733, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712476652015281e-05, + "loss": 3.9865, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711638057264229e-05, + "loss": 3.9817, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710799462513177e-05, + "loss": 3.9805, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709960867762125e-05, + "loss": 3.987, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709122273011073e-05, + "loss": 3.9644, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708283678260021e-05, + "loss": 3.969, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707445083508969e-05, + "loss": 3.9633, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.70660812663829e-05, + "loss": 3.9847, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705769531887238e-05, + "loss": 3.9635, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704930937136186e-05, + "loss": 3.9842, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704092342385134e-05, + "loss": 3.9609, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703253747634082e-05, + "loss": 3.9605, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024151528830305e-05, + "loss": 3.9678, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015781960123514e-05, + "loss": 3.961, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007396012612994e-05, + "loss": 3.9697, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6999010065102474e-05, + "loss": 3.9642, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990624117591954e-05, + "loss": 3.9514, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982238170081434e-05, + "loss": 3.9657, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973852222570914e-05, + "loss": 3.9604, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965466275060394e-05, + "loss": 3.9635, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695708032754987e-05, + "loss": 3.9573, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694871075884308e-05, + "loss": 3.9662, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694032481133256e-05, + "loss": 3.944, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693193886382204e-05, + "loss": 3.9666, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692355291631152e-05, + "loss": 3.9524, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691519972640847e-05, + "loss": 3.9592, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690681377889795e-05, + "loss": 3.9614, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689842783138743e-05, + "loss": 3.9542, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689004188387691e-05, + "loss": 3.9685, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688165593636639e-05, + "loss": 3.9754, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687326998885587e-05, + "loss": 3.9708, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686488404134534e-05, + "loss": 3.9609, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685649809383482e-05, + "loss": 3.9468, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848128525128036e-05, + "loss": 3.9395, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683974257761751e-05, + "loss": 3.9601, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831356630106996e-05, + "loss": 3.9683, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822970682596476e-05, + "loss": 3.9612, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.6814584735085956e-05, + "loss": 3.9448, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806198787575436e-05, + "loss": 3.9399, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797812840064916e-05, + "loss": 3.9506, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789426892554396e-05, + "loss": 3.9385, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.6781057323847605e-05, + "loss": 3.9455, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772671376337085e-05, + "loss": 3.9526, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764285428826565e-05, + "loss": 3.9522, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755915860119774e-05, + "loss": 3.9476, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674754629141298e-05, + "loss": 3.9502, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673916034390246e-05, + "loss": 3.9396, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673077439639194e-05, + "loss": 3.9508, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672238844888143e-05, + "loss": 3.9454, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671400250137091e-05, + "loss": 3.9333, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670561655386039e-05, + "loss": 3.9395, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.66972469851536e-05, + "loss": 3.9504, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668886103764308e-05, + "loss": 3.9577, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668047509013256e-05, + "loss": 3.9453, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667208914262204e-05, + "loss": 3.9412, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666371957391525e-05, + "loss": 3.9476, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665533362640473e-05, + "loss": 3.9312, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664694767889421e-05, + "loss": 3.9472, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663856173138369e-05, + "loss": 3.9514, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663017578387317e-05, + "loss": 3.9409, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662178983636265e-05, + "loss": 3.9473, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.6613420267655863e-05, + "loss": 3.9228, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660503432014534e-05, + "loss": 3.9229, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659664837263482e-05, + "loss": 3.9337, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.65882624251243e-05, + "loss": 3.9343, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657989285641751e-05, + "loss": 3.9439, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657150690890699e-05, + "loss": 3.9292, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656312096139647e-05, + "loss": 3.9246, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655473501388595e-05, + "loss": 3.9339, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654636544517916e-05, + "loss": 3.9446, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653797949766864e-05, + "loss": 3.9352, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652959355015812e-05, + "loss": 3.9421, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.65212076026476e-05, + "loss": 3.9268, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651283803394082e-05, + "loss": 3.9282, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.65044520864303e-05, + "loss": 3.9428, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6496082517723506e-05, + "loss": 3.9245, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487696570212986e-05, + "loss": 3.9261, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479310622702466e-05, + "loss": 3.9258, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470924675191946e-05, + "loss": 3.9219, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462538727681426e-05, + "loss": 3.9298, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454152780170906e-05, + "loss": 3.9293, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445766832660386e-05, + "loss": 3.9404, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437380885149866e-05, + "loss": 3.9174, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429011316443075e-05, + "loss": 3.9219, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420625368932555e-05, + "loss": 3.9437, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412239421422035e-05, + "loss": 3.9222, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640385347391152e-05, + "loss": 3.938, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395467526401e-05, + "loss": 3.9252, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387081578890475e-05, + "loss": 3.9381, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637871201018369e-05, + "loss": 3.9301, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637032606267317e-05, + "loss": 3.9162, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636194011516265e-05, + "loss": 3.916, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353554167652124e-05, + "loss": 3.9179, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345168220141604e-05, + "loss": 3.9286, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336782272631084e-05, + "loss": 3.9316, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328396325120564e-05, + "loss": 3.9289, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632002675641377e-05, + "loss": 3.924, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631164080890326e-05, + "loss": 3.9177, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630325486139274e-05, + "loss": 3.9199, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629486891388222e-05, + "loss": 3.9128, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628649934517543e-05, + "loss": 3.9215, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627811339766491e-05, + "loss": 3.9322, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626972745015439e-05, + "loss": 3.9212, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626134150264387e-05, + "loss": 3.9173, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625295555513335e-05, + "loss": 3.9145, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9506497383117676, + "eval_runtime": 568.5166, + "eval_samples_per_second": 671.205, + "eval_steps_per_second": 20.976, + "step": 228957 + }, + { + "epoch": 0.0, + "learning_rate": 4.624458598642656e-05, + "loss": 3.92, + "step": 229376 + }, + { + "epoch": 0.0, + "learning_rate": 4.623620003891604e-05, + "loss": 3.9238, + "step": 229888 + }, + { + "epoch": 0.0, + "learning_rate": 4.622781409140552e-05, + "loss": 3.9128, + "step": 230400 + }, + { + "epoch": 0.0, + "learning_rate": 4.6219428143895e-05, + "loss": 3.9097, + "step": 230912 + }, + { + "epoch": 0.0, + "learning_rate": 4.621104219638448e-05, + "loss": 3.9125, + "step": 231424 + }, + { + "epoch": 0.0, + "learning_rate": 4.620265624887396e-05, + "loss": 3.8922, + "step": 231936 + }, + { + "epoch": 0.0, + "learning_rate": 4.619427030136344e-05, + "loss": 3.9021, + "step": 232448 + }, + { + "epoch": 0.0, + "learning_rate": 4.6185884353852924e-05, + "loss": 3.9149, + "step": 232960 + }, + { + "epoch": 0.0, + "learning_rate": 4.6177498406342404e-05, + "loss": 3.9047, + "step": 233472 + }, + { + "epoch": 0.0, + "learning_rate": 4.616912883763561e-05, + "loss": 3.9113, + "step": 233984 + }, + { + "epoch": 0.0, + "learning_rate": 4.616074289012509e-05, + "loss": 3.9134, + "step": 234496 + }, + { + "epoch": 0.0, + "learning_rate": 4.615235694261457e-05, + "loss": 3.9088, + "step": 235008 + }, + { + "epoch": 0.0, + "learning_rate": 4.614397099510405e-05, + "loss": 3.903, + "step": 235520 + }, + { + "epoch": 0.0, + "learning_rate": 4.613560142639726e-05, + "loss": 3.9107, + "step": 236032 + }, + { + "epoch": 0.0, + "learning_rate": 4.612721547888674e-05, + "loss": 3.8999, + "step": 236544 + }, + { + "epoch": 0.0, + "learning_rate": 4.611882953137622e-05, + "loss": 3.898, + "step": 237056 + }, + { + "epoch": 0.0, + "learning_rate": 4.61104435838657e-05, + "loss": 3.8986, + "step": 237568 + }, + { + "epoch": 0.0, + "learning_rate": 4.610207401515891e-05, + "loss": 3.9038, + "step": 238080 + }, + { + "epoch": 0.0, + "learning_rate": 4.609368806764839e-05, + "loss": 3.9056, + "step": 238592 + }, + { + "epoch": 0.0, + "learning_rate": 4.608530212013788e-05, + "loss": 3.911, + "step": 239104 + }, + { + "epoch": 0.0, + "learning_rate": 4.607691617262736e-05, + "loss": 3.8999, + "step": 239616 + }, + { + "epoch": 0.0, + "learning_rate": 4.606853022511684e-05, + "loss": 3.9107, + "step": 240128 + }, + { + "epoch": 0.0, + "learning_rate": 4.606014427760631e-05, + "loss": 3.8979, + "step": 240640 + }, + { + "epoch": 0.0, + "learning_rate": 4.6051774708899526e-05, + "loss": 3.9, + "step": 241152 + }, + { + "epoch": 0.0, + "learning_rate": 4.6043388761389006e-05, + "loss": 3.9011, + "step": 241664 + }, + { + "epoch": 0.0, + "learning_rate": 4.603500281387848e-05, + "loss": 3.8972, + "step": 242176 + }, + { + "epoch": 0.0, + "learning_rate": 4.602661686636796e-05, + "loss": 3.9049, + "step": 242688 + }, + { + "epoch": 0.0, + "learning_rate": 4.6018247297661175e-05, + "loss": 3.8883, + "step": 243200 + }, + { + "epoch": 0.0, + "learning_rate": 4.6009861350150655e-05, + "loss": 3.9028, + "step": 243712 + }, + { + "epoch": 0.01, + "learning_rate": 4.600147540264013e-05, + "loss": 3.8901, + "step": 244224 + }, + { + "epoch": 0.01, + "learning_rate": 4.5993089455129615e-05, + "loss": 3.8924, + "step": 244736 + }, + { + "epoch": 0.01, + "learning_rate": 4.5984703507619095e-05, + "loss": 3.8964, + "step": 245248 + }, + { + "epoch": 0.01, + "learning_rate": 4.597633393891231e-05, + "loss": 3.9046, + "step": 245760 + }, + { + "epoch": 0.01, + "learning_rate": 4.5967947991401784e-05, + "loss": 3.8919, + "step": 246272 + }, + { + "epoch": 0.01, + "learning_rate": 4.5959562043891264e-05, + "loss": 3.8932, + "step": 246784 + }, + { + "epoch": 0.01, + "learning_rate": 4.5951176096380744e-05, + "loss": 3.8981, + "step": 247296 + }, + { + "epoch": 0.01, + "learning_rate": 4.594280652767395e-05, + "loss": 3.8937, + "step": 247808 + }, + { + "epoch": 0.01, + "learning_rate": 4.593442058016343e-05, + "loss": 3.9066, + "step": 248320 + }, + { + "epoch": 0.01, + "learning_rate": 4.592603463265291e-05, + "loss": 3.8916, + "step": 248832 + }, + { + "epoch": 0.01, + "learning_rate": 4.591764868514239e-05, + "loss": 3.8774, + "step": 249344 + }, + { + "epoch": 0.01, + "learning_rate": 4.590926273763187e-05, + "loss": 3.8854, + "step": 249856 + }, + { + "epoch": 0.01, + "learning_rate": 4.590087679012135e-05, + "loss": 3.8802, + "step": 250368 + }, + { + "epoch": 0.01, + "learning_rate": 4.589250722141457e-05, + "loss": 3.8995, + "step": 250880 + }, + { + "epoch": 0.01, + "learning_rate": 4.588412127390405e-05, + "loss": 3.8848, + "step": 251392 + }, + { + "epoch": 0.01, + "learning_rate": 4.587573532639353e-05, + "loss": 3.8927, + "step": 251904 + }, + { + "epoch": 0.01, + "learning_rate": 4.586734937888301e-05, + "loss": 3.8878, + "step": 252416 + }, + { + "epoch": 0.01, + "learning_rate": 4.585897981017622e-05, + "loss": 3.8904, + "step": 252928 + }, + { + "epoch": 0.01, + "learning_rate": 4.58505938626657e-05, + "loss": 3.895, + "step": 253440 + }, + { + "epoch": 0.01, + "learning_rate": 4.584220791515518e-05, + "loss": 3.8749, + "step": 253952 + }, + { + "epoch": 0.01, + "learning_rate": 4.583382196764466e-05, + "loss": 3.874, + "step": 254464 + }, + { + "epoch": 0.01, + "learning_rate": 4.582545239893787e-05, + "loss": 3.8797, + "step": 254976 + }, + { + "epoch": 0.01, + "learning_rate": 4.581706645142735e-05, + "loss": 3.8931, + "step": 255488 + }, + { + "epoch": 0.01, + "learning_rate": 4.580868050391683e-05, + "loss": 3.8755, + "step": 256000 + }, + { + "epoch": 0.01, + "learning_rate": 4.580029455640631e-05, + "loss": 3.8915, + "step": 256512 + }, + { + "epoch": 0.01, + "learning_rate": 4.579192498769952e-05, + "loss": 3.8718, + "step": 257024 + }, + { + "epoch": 0.01, + "learning_rate": 4.5783539040189e-05, + "loss": 3.8679, + "step": 257536 + }, + { + "epoch": 0.01, + "learning_rate": 4.577515309267848e-05, + "loss": 3.8814, + "step": 258048 + }, + { + "epoch": 0.01, + "learning_rate": 4.576676714516796e-05, + "loss": 3.868, + "step": 258560 + }, + { + "epoch": 0.01, + "learning_rate": 4.575839757646117e-05, + "loss": 3.8853, + "step": 259072 + }, + { + "epoch": 0.01, + "learning_rate": 4.575001162895065e-05, + "loss": 3.8773, + "step": 259584 + }, + { + "epoch": 0.01, + "learning_rate": 4.574162568144013e-05, + "loss": 3.8636, + "step": 260096 + }, + { + "epoch": 0.01, + "learning_rate": 4.573323973392961e-05, + "loss": 3.877, + "step": 260608 + }, + { + "epoch": 0.01, + "learning_rate": 4.572485378641909e-05, + "loss": 3.8719, + "step": 261120 + }, + { + "epoch": 0.01, + "learning_rate": 4.571646783890857e-05, + "loss": 3.8784, + "step": 261632 + }, + { + "epoch": 0.01, + "learning_rate": 4.570808189139805e-05, + "loss": 3.8663, + "step": 262144 + }, + { + "epoch": 0.01, + "learning_rate": 4.569971232269126e-05, + "loss": 3.8792, + "step": 262656 + }, + { + "epoch": 0.01, + "learning_rate": 4.569132637518074e-05, + "loss": 3.8572, + "step": 263168 + }, + { + "epoch": 0.01, + "learning_rate": 4.568294042767022e-05, + "loss": 3.8775, + "step": 263680 + }, + { + "epoch": 0.01, + "learning_rate": 4.567455448015971e-05, + "loss": 3.8625, + "step": 264192 + }, + { + "epoch": 0.01, + "learning_rate": 4.5666184911452916e-05, + "loss": 3.8713, + "step": 264704 + }, + { + "epoch": 0.01, + "learning_rate": 4.5657798963942396e-05, + "loss": 3.8762, + "step": 265216 + }, + { + "epoch": 0.01, + "learning_rate": 4.5649413016431876e-05, + "loss": 3.871, + "step": 265728 + }, + { + "epoch": 0.01, + "learning_rate": 4.5641027068921356e-05, + "loss": 3.878, + "step": 266240 + }, + { + "epoch": 0.01, + "learning_rate": 4.5632641121410836e-05, + "loss": 3.8916, + "step": 266752 + }, + { + "epoch": 0.01, + "learning_rate": 4.5624255173900316e-05, + "loss": 3.8843, + "step": 267264 + }, + { + "epoch": 0.01, + "learning_rate": 4.5615885605193525e-05, + "loss": 3.8726, + "step": 267776 + }, + { + "epoch": 0.01, + "learning_rate": 4.5607499657683005e-05, + "loss": 3.8661, + "step": 268288 + }, + { + "epoch": 0.01, + "learning_rate": 4.5599113710172485e-05, + "loss": 3.8591, + "step": 268800 + }, + { + "epoch": 0.01, + "learning_rate": 4.5590727762661965e-05, + "loss": 3.8747, + "step": 269312 + }, + { + "epoch": 0.01, + "learning_rate": 4.5582341815151445e-05, + "loss": 3.8845, + "step": 269824 + }, + { + "epoch": 0.01, + "learning_rate": 4.5573972246444654e-05, + "loss": 3.8763, + "step": 270336 + }, + { + "epoch": 0.01, + "learning_rate": 4.556558629893414e-05, + "loss": 3.86, + "step": 270848 + }, + { + "epoch": 0.01, + "learning_rate": 4.5557200351423614e-05, + "loss": 3.8571, + "step": 271360 + }, + { + "epoch": 0.01, + "learning_rate": 4.5548814403913094e-05, + "loss": 3.8717, + "step": 271872 + }, + { + "epoch": 0.01, + "learning_rate": 4.554044483520631e-05, + "loss": 3.8491, + "step": 272384 + }, + { + "epoch": 0.01, + "learning_rate": 4.553205888769579e-05, + "loss": 3.8654, + "step": 272896 + }, + { + "epoch": 0.01, + "learning_rate": 4.552367294018526e-05, + "loss": 3.8669, + "step": 273408 + }, + { + "epoch": 0.01, + "learning_rate": 4.551528699267474e-05, + "loss": 3.8694, + "step": 273920 + }, + { + "epoch": 0.01, + "learning_rate": 4.550691742396796e-05, + "loss": 3.8667, + "step": 274432 + }, + { + "epoch": 0.02, + "learning_rate": 4.549853147645744e-05, + "loss": 3.8716, + "step": 274944 + }, + { + "epoch": 0.02, + "learning_rate": 4.549014552894691e-05, + "loss": 3.8544, + "step": 275456 + }, + { + "epoch": 0.02, + "learning_rate": 4.548175958143639e-05, + "loss": 3.8663, + "step": 275968 + }, + { + "epoch": 0.02, + "learning_rate": 4.547339001272961e-05, + "loss": 3.8632, + "step": 276480 + }, + { + "epoch": 0.02, + "learning_rate": 4.546500406521909e-05, + "loss": 3.8548, + "step": 276992 + }, + { + "epoch": 0.02, + "learning_rate": 4.545661811770857e-05, + "loss": 3.8557, + "step": 277504 + }, + { + "epoch": 0.02, + "learning_rate": 4.544823217019805e-05, + "loss": 3.8725, + "step": 278016 + }, + { + "epoch": 0.02, + "learning_rate": 4.543984622268753e-05, + "loss": 3.8728, + "step": 278528 + }, + { + "epoch": 0.02, + "learning_rate": 4.5431476653980736e-05, + "loss": 3.8707, + "step": 279040 + }, + { + "epoch": 0.02, + "learning_rate": 4.5423090706470216e-05, + "loss": 3.8594, + "step": 279552 + }, + { + "epoch": 0.02, + "learning_rate": 4.5414704758959696e-05, + "loss": 3.8686, + "step": 280064 + }, + { + "epoch": 0.02, + "learning_rate": 4.5406318811449176e-05, + "loss": 3.8524, + "step": 280576 + }, + { + "epoch": 0.02, + "learning_rate": 4.5397949242742385e-05, + "loss": 3.8659, + "step": 281088 + }, + { + "epoch": 0.02, + "learning_rate": 4.5389563295231865e-05, + "loss": 3.8707, + "step": 281600 + }, + { + "epoch": 0.02, + "learning_rate": 4.5381177347721345e-05, + "loss": 3.859, + "step": 282112 + }, + { + "epoch": 0.02, + "learning_rate": 4.537279140021083e-05, + "loss": 3.8731, + "step": 282624 + }, + { + "epoch": 0.02, + "learning_rate": 4.536440545270031e-05, + "loss": 3.8398, + "step": 283136 + }, + { + "epoch": 0.02, + "learning_rate": 4.535601950518979e-05, + "loss": 3.8443, + "step": 283648 + }, + { + "epoch": 0.02, + "learning_rate": 4.5347649936483e-05, + "loss": 3.8548, + "step": 284160 + }, + { + "epoch": 0.02, + "learning_rate": 4.533926398897248e-05, + "loss": 3.8572, + "step": 284672 + }, + { + "epoch": 0.02, + "learning_rate": 4.533087804146196e-05, + "loss": 3.8661, + "step": 285184 + }, + { + "epoch": 0.02, + "learning_rate": 4.532249209395144e-05, + "loss": 3.851, + "step": 285696 + }, + { + "epoch": 0.02, + "learning_rate": 4.531410614644092e-05, + "loss": 3.8471, + "step": 286208 + }, + { + "epoch": 0.02, + "learning_rate": 4.530573657773413e-05, + "loss": 3.8563, + "step": 286720 + }, + { + "epoch": 0.02, + "learning_rate": 4.529735063022361e-05, + "loss": 3.8666, + "step": 287232 + }, + { + "epoch": 0.02, + "learning_rate": 4.528896468271309e-05, + "loss": 3.8596, + "step": 287744 + }, + { + "epoch": 0.02, + "learning_rate": 4.528057873520257e-05, + "loss": 3.8644, + "step": 288256 + }, + { + "epoch": 0.02, + "learning_rate": 4.527219278769205e-05, + "loss": 3.8509, + "step": 288768 + }, + { + "epoch": 0.02, + "learning_rate": 4.5263823218985266e-05, + "loss": 3.8509, + "step": 289280 + }, + { + "epoch": 0.02, + "learning_rate": 4.5255437271474746e-05, + "loss": 3.8682, + "step": 289792 + }, + { + "epoch": 0.02, + "learning_rate": 4.5247067702767955e-05, + "loss": 3.8497, + "step": 290304 + }, + { + "epoch": 0.02, + "learning_rate": 4.5238681755257435e-05, + "loss": 3.8467, + "step": 290816 + }, + { + "epoch": 0.02, + "learning_rate": 4.5230295807746915e-05, + "loss": 3.8514, + "step": 291328 + }, + { + "epoch": 0.02, + "learning_rate": 4.5221909860236395e-05, + "loss": 3.8437, + "step": 291840 + }, + { + "epoch": 0.02, + "learning_rate": 4.5213523912725875e-05, + "loss": 3.8556, + "step": 292352 + }, + { + "epoch": 0.02, + "learning_rate": 4.5205137965215355e-05, + "loss": 3.8524, + "step": 292864 + }, + { + "epoch": 0.02, + "learning_rate": 4.5196752017704834e-05, + "loss": 3.8661, + "step": 293376 + }, + { + "epoch": 0.02, + "learning_rate": 4.5188366070194314e-05, + "loss": 3.8443, + "step": 293888 + }, + { + "epoch": 0.02, + "learning_rate": 4.5179996501487524e-05, + "loss": 3.8442, + "step": 294400 + }, + { + "epoch": 0.02, + "learning_rate": 4.5171610553977003e-05, + "loss": 3.8712, + "step": 294912 + }, + { + "epoch": 0.02, + "learning_rate": 4.5163224606466483e-05, + "loss": 3.8464, + "step": 295424 + }, + { + "epoch": 0.02, + "learning_rate": 4.515483865895597e-05, + "loss": 3.8596, + "step": 295936 + }, + { + "epoch": 0.02, + "learning_rate": 4.514646909024918e-05, + "loss": 3.8557, + "step": 296448 + }, + { + "epoch": 0.02, + "learning_rate": 4.513808314273866e-05, + "loss": 3.863, + "step": 296960 + }, + { + "epoch": 0.02, + "learning_rate": 4.512969719522814e-05, + "loss": 3.8556, + "step": 297472 + }, + { + "epoch": 0.02, + "learning_rate": 4.512131124771762e-05, + "loss": 3.8462, + "step": 297984 + }, + { + "epoch": 0.02, + "learning_rate": 4.511294167901083e-05, + "loss": 3.84, + "step": 298496 + }, + { + "epoch": 0.02, + "learning_rate": 4.510455573150031e-05, + "loss": 3.8446, + "step": 299008 + }, + { + "epoch": 0.02, + "learning_rate": 4.509616978398979e-05, + "loss": 3.8533, + "step": 299520 + }, + { + "epoch": 0.02, + "learning_rate": 4.508778383647927e-05, + "loss": 3.8606, + "step": 300032 + }, + { + "epoch": 0.02, + "learning_rate": 4.507939788896874e-05, + "loss": 3.853, + "step": 300544 + }, + { + "epoch": 0.02, + "learning_rate": 4.507102832026196e-05, + "loss": 3.8554, + "step": 301056 + }, + { + "epoch": 0.02, + "learning_rate": 4.506264237275144e-05, + "loss": 3.8428, + "step": 301568 + }, + { + "epoch": 0.02, + "learning_rate": 4.5054256425240924e-05, + "loss": 3.8489, + "step": 302080 + }, + { + "epoch": 0.02, + "learning_rate": 4.50458704777304e-05, + "loss": 3.8379, + "step": 302592 + }, + { + "epoch": 0.02, + "learning_rate": 4.503750090902361e-05, + "loss": 3.8517, + "step": 303104 + }, + { + "epoch": 0.02, + "learning_rate": 4.502911496151309e-05, + "loss": 3.8548, + "step": 303616 + }, + { + "epoch": 0.02, + "learning_rate": 4.502072901400257e-05, + "loss": 3.8556, + "step": 304128 + }, + { + "epoch": 0.02, + "learning_rate": 4.5012343066492046e-05, + "loss": 3.8429, + "step": 304640 + }, + { + "epoch": 0.02, + "learning_rate": 4.500397349778526e-05, + "loss": 3.84, + "step": 305152 + }, + { + "epoch": 0.03, + "eval_loss": 3.909358024597168, + "eval_runtime": 575.0067, + "eval_samples_per_second": 663.629, + "eval_steps_per_second": 20.739, + "step": 305276 + }, + { + "epoch": 0.0, + "learning_rate": 4.499558755027474e-05, + "loss": 3.8506, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987201602764215e-05, + "loss": 3.8468, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978815655253695e-05, + "loss": 3.8427, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970429707743175e-05, + "loss": 3.8387, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496204376023266e-05, + "loss": 3.8419, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495365781272214e-05, + "loss": 3.8262, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494527186521162e-05, + "loss": 3.8331, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.49368859177011e-05, + "loss": 3.8379, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492851634899431e-05, + "loss": 3.8388, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492014678028752e-05, + "loss": 3.8423, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911760832777e-05, + "loss": 3.8409, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490337488526648e-05, + "loss": 3.8337, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489498893775596e-05, + "loss": 3.8356, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488660299024544e-05, + "loss": 3.8432, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487821704273492e-05, + "loss": 3.8317, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.48698310952244e-05, + "loss": 3.8282, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486144514771388e-05, + "loss": 3.8279, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853075579007095e-05, + "loss": 3.8385, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844689631496575e-05, + "loss": 3.8323, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836303683986055e-05, + "loss": 3.8459, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4827917736475535e-05, + "loss": 3.8294, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.4819548167768744e-05, + "loss": 3.8419, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.4811162220258224e-05, + "loss": 3.8328, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.4802776272747704e-05, + "loss": 3.8339, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.4794390325237184e-05, + "loss": 3.8307, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478602075653039e-05, + "loss": 3.8299, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477763480901987e-05, + "loss": 3.8379, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476924886150935e-05, + "loss": 3.8223, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476086291399883e-05, + "loss": 3.8332, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475247696648831e-05, + "loss": 3.8266, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474410739778153e-05, + "loss": 3.8203, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473572145027101e-05, + "loss": 3.8317, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472733550276049e-05, + "loss": 3.8366, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471894955524997e-05, + "loss": 3.8293, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471057998654318e-05, + "loss": 3.8251, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470219403903266e-05, + "loss": 3.8281, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469380809152214e-05, + "loss": 3.831, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468542214401162e-05, + "loss": 3.8394, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467705257530483e-05, + "loss": 3.8259, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466866662779431e-05, + "loss": 3.8104, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466028068028379e-05, + "loss": 3.8195, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465189473277327e-05, + "loss": 3.8165, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464352516406648e-05, + "loss": 3.8316, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463513921655596e-05, + "loss": 3.8215, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462675326904544e-05, + "loss": 3.83, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461836732153492e-05, + "loss": 3.8245, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460999775282813e-05, + "loss": 3.8235, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460161180531761e-05, + "loss": 3.8312, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459322585780709e-05, + "loss": 3.8127, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458483991029657e-05, + "loss": 3.8078, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457647034158978e-05, + "loss": 3.8183, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456808439407926e-05, + "loss": 3.824, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455969844656874e-05, + "loss": 3.8102, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455131249905822e-05, + "loss": 3.8277, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542942930351436e-05, + "loss": 3.8108, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534556982840916e-05, + "loss": 3.804, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526171035330396e-05, + "loss": 3.8177, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517785087819876e-05, + "loss": 3.8052, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509415519113085e-05, + "loss": 3.8251, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4501029571602565e-05, + "loss": 3.8175, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492643624092045e-05, + "loss": 3.798, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4484257676581525e-05, + "loss": 3.812, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475871729071e-05, + "loss": 3.8096, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.4467502160364214e-05, + "loss": 3.8222, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4459116212853694e-05, + "loss": 3.8033, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450730265343174e-05, + "loss": 3.8157, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442344317832654e-05, + "loss": 3.7981, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443397474912587e-05, + "loss": 3.8122, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442558880161535e-05, + "loss": 3.8035, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441720285410482e-05, + "loss": 3.808, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.44088169065943e-05, + "loss": 3.8166, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440044733788752e-05, + "loss": 3.8056, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.4392061390377e-05, + "loss": 3.817, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438367544286647e-05, + "loss": 3.8284, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437528949535595e-05, + "loss": 3.8252, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436691992664917e-05, + "loss": 3.8109, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435853397913865e-05, + "loss": 3.8061, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435014803162813e-05, + "loss": 3.7976, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434176208411761e-05, + "loss": 3.8106, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333392515410824e-05, + "loss": 3.8264, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.43250065679003e-05, + "loss": 3.8147, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431662062038978e-05, + "loss": 3.8023, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308234672879257e-05, + "loss": 3.7932, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429986510417247e-05, + "loss": 3.8169, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291479156661946e-05, + "loss": 3.7919, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283093209151426e-05, + "loss": 3.8027, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274707261640906e-05, + "loss": 3.8041, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426633769293412e-05, + "loss": 3.8071, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.42579517454236e-05, + "loss": 3.8088, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424956579791308e-05, + "loss": 3.8132, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424117985040256e-05, + "loss": 3.7962, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423281028169577e-05, + "loss": 3.8054, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422442433418525e-05, + "loss": 3.8038, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421603838667473e-05, + "loss": 3.798, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420765243916421e-05, + "loss": 3.7964, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419928287045742e-05, + "loss": 3.8146, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.41908969229469e-05, + "loss": 3.8123, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418251097543638e-05, + "loss": 3.8151, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417412502792586e-05, + "loss": 3.8025, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416575545921907e-05, + "loss": 3.8073, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157369511708555e-05, + "loss": 3.7958, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148983564198035e-05, + "loss": 3.8098, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140597616687515e-05, + "loss": 3.8105, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132228047980724e-05, + "loss": 3.8008, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123842100470204e-05, + "loss": 3.8166, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115456152959684e-05, + "loss": 3.784, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4107070205449164e-05, + "loss": 3.789, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409870063674237e-05, + "loss": 3.7948, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409031468923185e-05, + "loss": 3.7976, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408194512052507e-05, + "loss": 3.8095, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407355917301454e-05, + "loss": 3.7984, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406517322550402e-05, + "loss": 3.7872, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405678727799351e-05, + "loss": 3.7969, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404840133048299e-05, + "loss": 3.8098, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404001538297247e-05, + "loss": 3.8011, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403162943546195e-05, + "loss": 3.8096, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402324348795143e-05, + "loss": 3.7938, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401487391924464e-05, + "loss": 3.7935, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400648797173412e-05, + "loss": 3.8109, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399811840302733e-05, + "loss": 3.7949, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398973245551681e-05, + "loss": 3.7917, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3981346508006287e-05, + "loss": 3.7914, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.3972960560495767e-05, + "loss": 3.7913, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.3964574612985247e-05, + "loss": 3.8003, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956188665474726e-05, + "loss": 3.7977, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.3947802717964206e-05, + "loss": 3.8067, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939416770453686e-05, + "loss": 3.787, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.39310472017469e-05, + "loss": 3.7919, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392266125423638e-05, + "loss": 3.8114, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391427530672586e-05, + "loss": 3.7938, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390588935921534e-05, + "loss": 3.8029, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389751979050855e-05, + "loss": 3.8043, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388913384299803e-05, + "loss": 3.8031, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388074789548751e-05, + "loss": 3.8022, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387236194797699e-05, + "loss": 3.7889, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.38639923792702e-05, + "loss": 3.7872, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385560643175968e-05, + "loss": 3.793, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384722048424916e-05, + "loss": 3.7976, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383883453673864e-05, + "loss": 3.8022, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830464968031856e-05, + "loss": 3.8006, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822079020521336e-05, + "loss": 3.801, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813693073010816e-05, + "loss": 3.7907, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3805307125500296e-05, + "loss": 3.793, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796937556793505e-05, + "loss": 3.7808, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788551609282985e-05, + "loss": 3.7995, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3780165661772465e-05, + "loss": 3.8011, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771779714261945e-05, + "loss": 3.802, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763410145555154e-05, + "loss": 3.7869, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3755024198044634e-05, + "loss": 3.789, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.884547233581543, + "eval_runtime": 569.4418, + "eval_samples_per_second": 670.114, + "eval_steps_per_second": 20.942, + "step": 381595 + }, + { + "epoch": 0.0, + "learning_rate": 4.3746638250534114e-05, + "loss": 3.8056, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.3738252303023594e-05, + "loss": 3.7891, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.372986635551308e-05, + "loss": 3.7909, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.3721480408002554e-05, + "loss": 3.7824, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.3713094460492034e-05, + "loss": 3.7876, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.3704708512981514e-05, + "loss": 3.7754, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.3696322565470993e-05, + "loss": 3.7819, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.3687936617960473e-05, + "loss": 3.7794, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.367956704925368e-05, + "loss": 3.7874, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.36711974805469e-05, + "loss": 3.7931, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.366281153303637e-05, + "loss": 3.7848, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.365442558552585e-05, + "loss": 3.782, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.364603963801533e-05, + "loss": 3.7868, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363765369050482e-05, + "loss": 3.7893, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.36292677429943e-05, + "loss": 3.7789, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.362088179548378e-05, + "loss": 3.7762, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.361249584797326e-05, + "loss": 3.7757, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.360412627926647e-05, + "loss": 3.7841, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.359574033175595e-05, + "loss": 3.7823, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.358735438424543e-05, + "loss": 3.7942, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357896843673491e-05, + "loss": 3.7794, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.3570598868028116e-05, + "loss": 3.7892, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.3562212920517596e-05, + "loss": 3.7833, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.3553826973007076e-05, + "loss": 3.7811, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.3545441025496556e-05, + "loss": 3.7791, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.353707145678977e-05, + "loss": 3.7788, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.352868550927925e-05, + "loss": 3.7876, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.352029956176873e-05, + "loss": 3.7681, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.351191361425821e-05, + "loss": 3.786, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.350354404555142e-05, + "loss": 3.7745, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.34951580980409e-05, + "loss": 3.7667, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.348677215053038e-05, + "loss": 3.7819, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.347838620301986e-05, + "loss": 3.7835, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.347001663431307e-05, + "loss": 3.7834, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.346163068680255e-05, + "loss": 3.7764, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.345324473929203e-05, + "loss": 3.7757, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.344485879178151e-05, + "loss": 3.7794, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.3436489223074726e-05, + "loss": 3.7922, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.3428103275564206e-05, + "loss": 3.7769, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.3419717328053685e-05, + "loss": 3.7611, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.3411331380543165e-05, + "loss": 3.7697, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.3402961811836375e-05, + "loss": 3.7649, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.3394575864325854e-05, + "loss": 3.7811, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.3386189916815334e-05, + "loss": 3.7748, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.3377803969304814e-05, + "loss": 3.7764, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.3369434400598024e-05, + "loss": 3.7777, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.3361048453087503e-05, + "loss": 3.7749, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.3352662505576983e-05, + "loss": 3.7828, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.334427655806646e-05, + "loss": 3.7644, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333590698935968e-05, + "loss": 3.7554, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.332752104184916e-05, + "loss": 3.772, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.331913509433864e-05, + "loss": 3.7687, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.331074914682812e-05, + "loss": 3.7663, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.330237957812133e-05, + "loss": 3.7772, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.329399363061081e-05, + "loss": 3.7601, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.328560768310029e-05, + "loss": 3.7587, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.327722173558977e-05, + "loss": 3.7682, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.326885216688298e-05, + "loss": 3.7581, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.326046621937246e-05, + "loss": 3.776, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.325208027186194e-05, + "loss": 3.7668, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.324369432435142e-05, + "loss": 3.7583, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.3235324755644626e-05, + "loss": 3.7603, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.322693880813411e-05, + "loss": 3.7556, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.321855286062359e-05, + "loss": 3.7779, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.321016691311307e-05, + "loss": 3.7564, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320179734440628e-05, + "loss": 3.7722, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.319341139689576e-05, + "loss": 3.7484, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.318502544938524e-05, + "loss": 3.7638, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.317663950187472e-05, + "loss": 3.7574, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.316826993316793e-05, + "loss": 3.7588, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.315988398565741e-05, + "loss": 3.7671, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.315149803814689e-05, + "loss": 3.7618, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.314311209063637e-05, + "loss": 3.766, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.313474252192958e-05, + "loss": 3.7791, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.3126356574419067e-05, + "loss": 3.776, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.3117970626908546e-05, + "loss": 3.7666, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.3109584679398026e-05, + "loss": 3.7601, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.3101215110691236e-05, + "loss": 3.7532, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.3092829163180715e-05, + "loss": 3.7617, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.3084443215670195e-05, + "loss": 3.7772, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.3076057268159675e-05, + "loss": 3.7668, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.3067687699452885e-05, + "loss": 3.7565, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.3059301751942364e-05, + "loss": 3.7448, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.3050915804431844e-05, + "loss": 3.7727, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.3042529856921324e-05, + "loss": 3.7401, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.3034160288214533e-05, + "loss": 3.7579, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.302577434070402e-05, + "loss": 3.7574, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.30173883931935e-05, + "loss": 3.7613, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.300900244568298e-05, + "loss": 3.762, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.300063287697619e-05, + "loss": 3.7696, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.299224692946567e-05, + "loss": 3.7476, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.298386098195515e-05, + "loss": 3.7571, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.297547503444463e-05, + "loss": 3.7608, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.296710546573784e-05, + "loss": 3.7528, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.295871951822732e-05, + "loss": 3.7503, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.29503335707168e-05, + "loss": 3.7674, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294194762320628e-05, + "loss": 3.7627, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293357805449949e-05, + "loss": 3.7742, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.2925192106988974e-05, + "loss": 3.7562, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.2916806159478454e-05, + "loss": 3.7601, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.290843659077166e-05, + "loss": 3.7493, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.290005064326114e-05, + "loss": 3.7624, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.289166469575062e-05, + "loss": 3.7688, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.28832787482401e-05, + "loss": 3.754, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.287490917953331e-05, + "loss": 3.7696, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.286652323202279e-05, + "loss": 3.7392, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.285813728451227e-05, + "loss": 3.7479, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.284975133700175e-05, + "loss": 3.7449, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.284138176829496e-05, + "loss": 3.753, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.283301219958818e-05, + "loss": 3.7648, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.282462625207766e-05, + "loss": 3.7598, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281624030456714e-05, + "loss": 3.7333, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.2807854357056617e-05, + "loss": 3.7583, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.2799468409546097e-05, + "loss": 3.7644, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.2791082462035576e-05, + "loss": 3.7613, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.278269651452505e-05, + "loss": 3.7604, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.277431056701453e-05, + "loss": 3.7499, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.2765940998307746e-05, + "loss": 3.7483, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.2757555050797225e-05, + "loss": 3.7671, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.2749185482090435e-05, + "loss": 3.7502, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.2740799534579915e-05, + "loss": 3.7499, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.2732413587069394e-05, + "loss": 3.7443, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.2724027639558874e-05, + "loss": 3.7471, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.2715641692048354e-05, + "loss": 3.7556, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.2707255744537834e-05, + "loss": 3.7534, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.2698869797027314e-05, + "loss": 3.7619, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.2690483849516794e-05, + "loss": 3.7463, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.268211428081e-05, + "loss": 3.7461, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.267372833329948e-05, + "loss": 3.7677, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.266534238578896e-05, + "loss": 3.7493, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.265695643827844e-05, + "loss": 3.7575, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.264858686957165e-05, + "loss": 3.7614, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.264020092206113e-05, + "loss": 3.7606, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263181497455062e-05, + "loss": 3.7591, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.26234290270401e-05, + "loss": 3.7475, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.261505945833331e-05, + "loss": 3.7403, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.260667351082279e-05, + "loss": 3.7475, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.259828756331227e-05, + "loss": 3.7536, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.258990161580175e-05, + "loss": 3.7621, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.258153204709496e-05, + "loss": 3.7553, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.257314609958444e-05, + "loss": 3.7545, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.256476015207392e-05, + "loss": 3.7508, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.25563742045634e-05, + "loss": 3.7538, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.2548004635856606e-05, + "loss": 3.7421, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.2539618688346086e-05, + "loss": 3.7471, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.253123274083557e-05, + "loss": 3.7599, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252284679332505e-05, + "loss": 3.7608, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.251447722461826e-05, + "loss": 3.743, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.250609127710774e-05, + "loss": 3.7449, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.8676059246063232, + "eval_runtime": 590.5677, + "eval_samples_per_second": 646.143, + "eval_steps_per_second": 20.192, + "step": 457914 + }, + { + "epoch": 0.0, + "learning_rate": 4.249772170840095e-05, + "loss": 3.7648, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248933576089043e-05, + "loss": 3.7487, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248094981337991e-05, + "loss": 3.7455, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247256386586939e-05, + "loss": 3.7454, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246417791835887e-05, + "loss": 3.7412, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245579197084835e-05, + "loss": 3.7354, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244740602333783e-05, + "loss": 3.7364, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243902007582731e-05, + "loss": 3.7395, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243065050712052e-05, + "loss": 3.7452, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422264559610006e-05, + "loss": 3.749, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413894990903215e-05, + "loss": 3.7474, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.2405509043392695e-05, + "loss": 3.7345, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.2397123095882175e-05, + "loss": 3.7492, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388737148371655e-05, + "loss": 3.7439, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380351200861135e-05, + "loss": 3.7424, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2371965253350615e-05, + "loss": 3.7291, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363579305840095e-05, + "loss": 3.7316, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355209737133304e-05, + "loss": 3.7464, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346823789622784e-05, + "loss": 3.7379, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.2338437842112264e-05, + "loss": 3.7531, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2330051894601744e-05, + "loss": 3.7373, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232168232589496e-05, + "loss": 3.747, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231329637838444e-05, + "loss": 3.7407, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230491043087392e-05, + "loss": 3.7405, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.22965244833634e-05, + "loss": 3.7365, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228815491465661e-05, + "loss": 3.7369, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227976896714609e-05, + "loss": 3.747, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227138301963557e-05, + "loss": 3.7285, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226299707212505e-05, + "loss": 3.7454, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225462750341826e-05, + "loss": 3.7353, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224624155590774e-05, + "loss": 3.7245, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223785560839722e-05, + "loss": 3.7407, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.22294696608867e-05, + "loss": 3.7423, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2221100092179914e-05, + "loss": 3.7465, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212714144669394e-05, + "loss": 3.7338, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2204328197158874e-05, + "loss": 3.7379, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2195942249648353e-05, + "loss": 3.7375, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218757268094156e-05, + "loss": 3.7476, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217918673343104e-05, + "loss": 3.7387, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217080078592052e-05, + "loss": 3.7194, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216241483841e-05, + "loss": 3.7286, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215404526970321e-05, + "loss": 3.7255, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214565932219269e-05, + "loss": 3.7447, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213727337468217e-05, + "loss": 3.7361, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212888742717165e-05, + "loss": 3.734, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212051785846487e-05, + "loss": 3.7402, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211213191095435e-05, + "loss": 3.7334, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210374596344383e-05, + "loss": 3.7421, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209536001593331e-05, + "loss": 3.7262, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.2086990447226516e-05, + "loss": 3.7183, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2078604499715996e-05, + "loss": 3.7313, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070218552205476e-05, + "loss": 3.7238, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206183260469495e-05, + "loss": 3.7296, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2053463035988165e-05, + "loss": 3.731, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045077088477645e-05, + "loss": 3.724, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036691140967125e-05, + "loss": 3.7197, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028305193456605e-05, + "loss": 3.726, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201993562474982e-05, + "loss": 3.7207, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.20115496772393e-05, + "loss": 3.7349, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200316372972878e-05, + "loss": 3.727, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994777782218254e-05, + "loss": 3.7175, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198640821351147e-05, + "loss": 3.7239, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197802226600095e-05, + "loss": 3.7114, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196963631849042e-05, + "loss": 3.741, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196126674978364e-05, + "loss": 3.7201, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195289718107685e-05, + "loss": 3.7295, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194451123356633e-05, + "loss": 3.7152, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193612528605581e-05, + "loss": 3.7181, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192773933854529e-05, + "loss": 3.7207, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1919353391034775e-05, + "loss": 3.7194, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191096744352425e-05, + "loss": 3.7297, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190258149601373e-05, + "loss": 3.7226, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189419554850321e-05, + "loss": 3.7283, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885825979796424e-05, + "loss": 3.7399, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.18774400322859e-05, + "loss": 3.7359, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186905408477538e-05, + "loss": 3.7307, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186068451606859e-05, + "loss": 3.7215, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.18523149473618e-05, + "loss": 3.7158, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184392899985128e-05, + "loss": 3.7228, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183554305234076e-05, + "loss": 3.7373, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182715710483024e-05, + "loss": 3.7298, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181877115731972e-05, + "loss": 3.7194, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.18103852098092e-05, + "loss": 3.704, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180199926229868e-05, + "loss": 3.7364, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.17936296935919e-05, + "loss": 3.7004, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178524374608137e-05, + "loss": 3.7207, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177685779857085e-05, + "loss": 3.7221, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176847185106033e-05, + "loss": 3.7215, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.176008590354981e-05, + "loss": 3.7281, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175169995603929e-05, + "loss": 3.7326, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174331400852877e-05, + "loss": 3.708, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173492806101825e-05, + "loss": 3.7218, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726558492311466e-05, + "loss": 3.7234, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1718172544800946e-05, + "loss": 3.7149, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.1709786597290426e-05, + "loss": 3.7132, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1701400649779906e-05, + "loss": 3.7311, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693031081073115e-05, + "loss": 3.7251, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684645133562595e-05, + "loss": 3.7404, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1676259186052075e-05, + "loss": 3.7176, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667889617345284e-05, + "loss": 3.7252, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1659503669834764e-05, + "loss": 3.7122, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1651117722324244e-05, + "loss": 3.7238, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642731774813724e-05, + "loss": 3.7315, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163436220610693e-05, + "loss": 3.7215, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162597625859642e-05, + "loss": 3.7292, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.16175903110859e-05, + "loss": 3.7055, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160920436357538e-05, + "loss": 3.7059, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160083479486859e-05, + "loss": 3.704, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159244884735807e-05, + "loss": 3.7156, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158407927865128e-05, + "loss": 3.7272, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157569333114076e-05, + "loss": 3.7258, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156730738363024e-05, + "loss": 3.6958, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155892143611972e-05, + "loss": 3.7188, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.15505354886092e-05, + "loss": 3.7282, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154214954109868e-05, + "loss": 3.7253, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153376359358816e-05, + "loss": 3.7231, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152537764607764e-05, + "loss": 3.7141, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151700807737085e-05, + "loss": 3.7151, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150862212986033e-05, + "loss": 3.7263, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150023618234981e-05, + "loss": 3.7162, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149185023483929e-05, + "loss": 3.7117, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.14834806661325e-05, + "loss": 3.7068, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147509471862198e-05, + "loss": 3.711, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146670877111146e-05, + "loss": 3.721, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145832282360094e-05, + "loss": 3.7188, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144995325489415e-05, + "loss": 3.7234, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144156730738363e-05, + "loss": 3.7123, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143318135987311e-05, + "loss": 3.7099, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142481179116632e-05, + "loss": 3.7306, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141642584365581e-05, + "loss": 3.7096, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140803989614529e-05, + "loss": 3.7232, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139965394863477e-05, + "loss": 3.7275, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1391284379927976e-05, + "loss": 3.7236, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382898432417456e-05, + "loss": 3.7221, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1374512484906936e-05, + "loss": 3.717, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1366142916200145e-05, + "loss": 3.7044, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357756968689625e-05, + "loss": 3.7108, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349371021179105e-05, + "loss": 3.7146, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340985073668585e-05, + "loss": 3.7284, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1332599126158065e-05, + "loss": 3.7167, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324213178647545e-05, + "loss": 3.7233, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315827231137025e-05, + "loss": 3.7137, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307441283626505e-05, + "loss": 3.7165, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129907171491972e-05, + "loss": 3.7044, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.12906857674092e-05, + "loss": 3.7138, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128229981989868e-05, + "loss": 3.7249, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273913872388154e-05, + "loss": 3.7254, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126554430368137e-05, + "loss": 3.7052, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125715835617085e-05, + "loss": 3.7126, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.8570079803466797, + "eval_runtime": 575.5369, + "eval_samples_per_second": 663.017, + "eval_steps_per_second": 20.72, + "step": 534233 + }, + { + "epoch": 0.0, + "learning_rate": 4.124878878746406e-05, + "loss": 3.7336, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.124040283995354e-05, + "loss": 3.7112, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.123201689244302e-05, + "loss": 3.7108, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.12236309449325e-05, + "loss": 3.7114, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.121524499742198e-05, + "loss": 3.7023, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.120685904991146e-05, + "loss": 3.7055, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.119847310240094e-05, + "loss": 3.6959, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.119008715489042e-05, + "loss": 3.7097, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.118171758618363e-05, + "loss": 3.7066, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.117333163867311e-05, + "loss": 3.7125, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.116496206996632e-05, + "loss": 3.7098, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.1156576122455796e-05, + "loss": 3.702, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.1148190174945276e-05, + "loss": 3.7142, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.1139804227434756e-05, + "loss": 3.7055, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.1131418279924236e-05, + "loss": 3.7136, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.1123032332413716e-05, + "loss": 3.6918, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.1114646384903196e-05, + "loss": 3.6983, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110627681619641e-05, + "loss": 3.7102, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109789086868589e-05, + "loss": 3.7025, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108950492117537e-05, + "loss": 3.717, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.108111897366485e-05, + "loss": 3.7061, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.107274940495806e-05, + "loss": 3.7114, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106436345744754e-05, + "loss": 3.7074, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.105599388874075e-05, + "loss": 3.7047, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.104760794123023e-05, + "loss": 3.7053, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.103922199371971e-05, + "loss": 3.6995, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.103083604620919e-05, + "loss": 3.7124, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.102245009869867e-05, + "loss": 3.7014, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.101406415118815e-05, + "loss": 3.7091, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.1005678203677637e-05, + "loss": 3.6974, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.0997308634970846e-05, + "loss": 3.6943, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.0988939066264055e-05, + "loss": 3.7071, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.0980553118753535e-05, + "loss": 3.7074, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.0972167171243015e-05, + "loss": 3.7095, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.0963781223732495e-05, + "loss": 3.7052, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.0955395276221975e-05, + "loss": 3.6995, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.0947009328711455e-05, + "loss": 3.7053, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.0938623381200935e-05, + "loss": 3.7109, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.0930237433690414e-05, + "loss": 3.7057, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.0921867864983624e-05, + "loss": 3.6883, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.091349829627684e-05, + "loss": 3.6922, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.090511234876632e-05, + "loss": 3.692, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.08967264012558e-05, + "loss": 3.7103, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.088834045374528e-05, + "loss": 3.7024, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.087995450623476e-05, + "loss": 3.6969, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.087156855872424e-05, + "loss": 3.7115, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.086318261121372e-05, + "loss": 3.6986, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.08547966637032e-05, + "loss": 3.7094, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.084642709499641e-05, + "loss": 3.6928, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.083804114748589e-05, + "loss": 3.6859, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.082965519997537e-05, + "loss": 3.6965, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082126925246485e-05, + "loss": 3.6956, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081289968375806e-05, + "loss": 3.692, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080451373624754e-05, + "loss": 3.7004, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079614416754075e-05, + "loss": 3.6923, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078775822003023e-05, + "loss": 3.6835, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.077937227251971e-05, + "loss": 3.6977, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.077098632500919e-05, + "loss": 3.6842, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.076260037749867e-05, + "loss": 3.7, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075421442998815e-05, + "loss": 3.6937, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074584486128136e-05, + "loss": 3.688, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.073745891377084e-05, + "loss": 3.6889, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072907296626032e-05, + "loss": 3.6812, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.07206870187498e-05, + "loss": 3.7037, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071230107123928e-05, + "loss": 3.6854, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.070393150253249e-05, + "loss": 3.6962, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.069554555502198e-05, + "loss": 3.687, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.068715960751146e-05, + "loss": 3.6843, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.067877366000094e-05, + "loss": 3.6849, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.0670404091294147e-05, + "loss": 3.6902, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.0662018143783627e-05, + "loss": 3.6941, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.0653632196273106e-05, + "loss": 3.6895, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.064524624876258e-05, + "loss": 3.6955, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.063686030125206e-05, + "loss": 3.7066, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.0628490732545275e-05, + "loss": 3.7043, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.0620104785034755e-05, + "loss": 3.6951, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.061171883752423e-05, + "loss": 3.696, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.0603332890013715e-05, + "loss": 3.678, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.0594946942503195e-05, + "loss": 3.6911, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.0586560994992675e-05, + "loss": 3.7055, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.0578175047482155e-05, + "loss": 3.6966, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.0569789099971635e-05, + "loss": 3.6916, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.0561419531264844e-05, + "loss": 3.6724, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.0553033583754324e-05, + "loss": 3.6979, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.0544647636243804e-05, + "loss": 3.6736, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.0536261688733284e-05, + "loss": 3.6863, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.0527875741222764e-05, + "loss": 3.6844, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.0519489793712244e-05, + "loss": 3.6898, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.0511103846201724e-05, + "loss": 3.697, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.050273427749493e-05, + "loss": 3.6969, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.049434832998441e-05, + "loss": 3.6804, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.04859623824739e-05, + "loss": 3.6937, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.047757643496338e-05, + "loss": 3.6863, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.046920686625659e-05, + "loss": 3.6841, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.046082091874607e-05, + "loss": 3.679, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.045243497123555e-05, + "loss": 3.6965, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.044404902372503e-05, + "loss": 3.694, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.043569583382197e-05, + "loss": 3.7076, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.042730988631145e-05, + "loss": 3.6913, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041892393880093e-05, + "loss": 3.6914, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.041053799129041e-05, + "loss": 3.6793, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040215204377989e-05, + "loss": 3.6937, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039376609626937e-05, + "loss": 3.6963, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.0385380148758853e-05, + "loss": 3.6916, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.0376994201248333e-05, + "loss": 3.6965, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036862463254154e-05, + "loss": 3.6773, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.036025506383475e-05, + "loss": 3.6736, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.035186911632423e-05, + "loss": 3.6764, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.034348316881371e-05, + "loss": 3.6821, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.033509722130319e-05, + "loss": 3.6955, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.03267276525964e-05, + "loss": 3.6934, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.031834170508588e-05, + "loss": 3.662, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.030995575757536e-05, + "loss": 3.6917, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.030156981006484e-05, + "loss": 3.6969, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.029318386255432e-05, + "loss": 3.6914, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.028479791504381e-05, + "loss": 3.693, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.027641196753329e-05, + "loss": 3.6871, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.026802602002277e-05, + "loss": 3.679, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.0259656451315976e-05, + "loss": 3.6957, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.0251270503805456e-05, + "loss": 3.6872, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.0242884556294936e-05, + "loss": 3.6801, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.0234514987588145e-05, + "loss": 3.6735, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.0226129040077625e-05, + "loss": 3.6818, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.0217743092567105e-05, + "loss": 3.6872, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.0209357145056585e-05, + "loss": 3.6844, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.0200971197546065e-05, + "loss": 3.6947, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.0192585250035545e-05, + "loss": 3.6807, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.0184199302525025e-05, + "loss": 3.6794, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.0175813355014505e-05, + "loss": 3.7009, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.0167443786307714e-05, + "loss": 3.6768, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.0159057838797194e-05, + "loss": 3.6914, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.0150671891286674e-05, + "loss": 3.6982, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014230232257989e-05, + "loss": 3.6901, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.013391637506936e-05, + "loss": 3.6923, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.012553042755884e-05, + "loss": 3.6875, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.011714448004832e-05, + "loss": 3.6733, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.010877491134154e-05, + "loss": 3.6791, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.010038896383101e-05, + "loss": 3.6868, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.009200301632049e-05, + "loss": 3.6916, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.008361706880998e-05, + "loss": 3.6883, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.007523112129946e-05, + "loss": 3.6926, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.006684517378894e-05, + "loss": 3.6808, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.005847560508215e-05, + "loss": 3.6865, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.005008965757163e-05, + "loss": 3.6745, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.004170371006111e-05, + "loss": 3.686, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003331776255059e-05, + "loss": 3.6939, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002493181504007e-05, + "loss": 3.6962, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.001654586752955e-05, + "loss": 3.6717, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.000815992001903e-05, + "loss": 3.6841, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.850813150405884, + "eval_runtime": 566.9772, + "eval_samples_per_second": 673.027, + "eval_steps_per_second": 21.033, + "step": 610552 + }, + { + "epoch": 0.0, + "learning_rate": 3.9999790351312236e-05, + "loss": 3.7043, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.9991404403801716e-05, + "loss": 3.6854, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.9983018456291196e-05, + "loss": 3.6816, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9974632508780676e-05, + "loss": 3.6827, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996626294007389e-05, + "loss": 3.6711, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995787699256337e-05, + "loss": 3.6736, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994949104505285e-05, + "loss": 3.6714, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994110509754233e-05, + "loss": 3.673, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993271915003181e-05, + "loss": 3.6766, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992434958132502e-05, + "loss": 3.6854, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991598001261823e-05, + "loss": 3.6804, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990759406510771e-05, + "loss": 3.6761, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989920811759719e-05, + "loss": 3.6843, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989082217008667e-05, + "loss": 3.6708, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988243622257615e-05, + "loss": 3.6862, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987405027506563e-05, + "loss": 3.6633, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986566432755512e-05, + "loss": 3.6681, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857278380044597e-05, + "loss": 3.682, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848892432534077e-05, + "loss": 3.6735, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9840522863827286e-05, + "loss": 3.687, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.9832136916316766e-05, + "loss": 3.6772, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823750968806246e-05, + "loss": 3.6791, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9815365021295726e-05, + "loss": 3.6799, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.98069790737852e-05, + "loss": 3.6749, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979859312627468e-05, + "loss": 3.6774, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979020717876416e-05, + "loss": 3.6709, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978182123125364e-05, + "loss": 3.6827, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9773451662546854e-05, + "loss": 3.6694, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9765065715036334e-05, + "loss": 3.6826, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9756679767525814e-05, + "loss": 3.6671, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748293820015294e-05, + "loss": 3.6625, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9739924251308503e-05, + "loss": 3.6777, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973153830379798e-05, + "loss": 3.6791, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972315235628746e-05, + "loss": 3.6785, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971476640877694e-05, + "loss": 3.6749, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970638046126642e-05, + "loss": 3.6737, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.96979945137559e-05, + "loss": 3.672, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968962494504911e-05, + "loss": 3.6828, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968123899753859e-05, + "loss": 3.6768, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967285305002807e-05, + "loss": 3.6593, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966446710251755e-05, + "loss": 3.6639, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965608115500703e-05, + "loss": 3.6621, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964771158630025e-05, + "loss": 3.6802, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963932563878973e-05, + "loss": 3.6789, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963093969127921e-05, + "loss": 3.6639, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962255374376869e-05, + "loss": 3.6841, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961416779625817e-05, + "loss": 3.6682, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960579822755138e-05, + "loss": 3.6806, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959741228004086e-05, + "loss": 3.6667, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958902633253034e-05, + "loss": 3.6596, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958064038501982e-05, + "loss": 3.6651, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.95722544375093e-05, + "loss": 3.6645, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.9563884868802506e-05, + "loss": 3.6714, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9555498921291986e-05, + "loss": 3.6653, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954711297378147e-05, + "loss": 3.6672, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953872702627095e-05, + "loss": 3.6549, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953035745756416e-05, + "loss": 3.6688, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952197151005364e-05, + "loss": 3.6572, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951358556254312e-05, + "loss": 3.6692, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.95051996150326e-05, + "loss": 3.6607, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949683004632581e-05, + "loss": 3.6647, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948844409881529e-05, + "loss": 3.6614, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.948005815130477e-05, + "loss": 3.6533, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947167220379425e-05, + "loss": 3.6741, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946328625628373e-05, + "loss": 3.6576, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945491668757694e-05, + "loss": 3.6682, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446530740066426e-05, + "loss": 3.66, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9438144792555906e-05, + "loss": 3.6549, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429758845045386e-05, + "loss": 3.6576, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9421389276338595e-05, + "loss": 3.6604, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9413003328828075e-05, + "loss": 3.6642, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9404617381317555e-05, + "loss": 3.6641, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939623143380703e-05, + "loss": 3.6647, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938784548629651e-05, + "loss": 3.6854, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937945953878599e-05, + "loss": 3.6744, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.9371089970079204e-05, + "loss": 3.6652, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936270402256868e-05, + "loss": 3.6682, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.9354318075058164e-05, + "loss": 3.651, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.9345932127547644e-05, + "loss": 3.6604, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933756255884086e-05, + "loss": 3.6753, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932917661133033e-05, + "loss": 3.6726, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932079066381981e-05, + "loss": 3.66, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931240471630929e-05, + "loss": 3.6474, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930401876879877e-05, + "loss": 3.6697, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929564920009198e-05, + "loss": 3.6424, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928726325258146e-05, + "loss": 3.6601, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927887730507094e-05, + "loss": 3.6583, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927049135756042e-05, + "loss": 3.6589, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.92621054100499e-05, + "loss": 3.6723, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925371946253938e-05, + "loss": 3.6681, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924533351502886e-05, + "loss": 3.655, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923694756751835e-05, + "loss": 3.6593, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922857799881156e-05, + "loss": 3.6603, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922019205130104e-05, + "loss": 3.6573, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921180610379052e-05, + "loss": 3.6528, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920342015628e-05, + "loss": 3.6662, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919503420876948e-05, + "loss": 3.6688, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.9186664640062686e-05, + "loss": 3.6825, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178278692552166e-05, + "loss": 3.659, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169892745041646e-05, + "loss": 3.6657, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161506797531126e-05, + "loss": 3.6542, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9153137228824335e-05, + "loss": 3.6614, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144751281313815e-05, + "loss": 3.6712, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.91363653338033e-05, + "loss": 3.6639, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912797938629278e-05, + "loss": 3.672, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911959343878226e-05, + "loss": 3.6485, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911122387007547e-05, + "loss": 3.6495, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910283792256495e-05, + "loss": 3.6495, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909445197505443e-05, + "loss": 3.6574, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908606602754391e-05, + "loss": 3.6628, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907769645883712e-05, + "loss": 3.6665, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.90693105113266e-05, + "loss": 3.6364, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906092456381608e-05, + "loss": 3.6656, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905253861630556e-05, + "loss": 3.6689, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904416904759877e-05, + "loss": 3.6609, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035783100088256e-05, + "loss": 3.6651, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027397152577736e-05, + "loss": 3.6626, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9019011205067216e-05, + "loss": 3.6488, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010625257556696e-05, + "loss": 3.669, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.9002255688849905e-05, + "loss": 3.6661, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993869741339385e-05, + "loss": 3.65, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8985483793828865e-05, + "loss": 3.6485, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897709784631834e-05, + "loss": 3.6557, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.8968728277611554e-05, + "loss": 3.6581, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8960342330101034e-05, + "loss": 3.6561, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8951956382590514e-05, + "loss": 3.666, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8943570435079994e-05, + "loss": 3.6588, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8935184487569473e-05, + "loss": 3.6503, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8926798540058953e-05, + "loss": 3.6746, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891841259254843e-05, + "loss": 3.6515, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891004302384164e-05, + "loss": 3.6645, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890165707633112e-05, + "loss": 3.6727, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.88932711288206e-05, + "loss": 3.6617, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888488518131008e-05, + "loss": 3.6662, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887651561260329e-05, + "loss": 3.6616, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886812966509277e-05, + "loss": 3.6471, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885974371758225e-05, + "loss": 3.6546, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885135777007173e-05, + "loss": 3.6573, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884298820136494e-05, + "loss": 3.6685, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883460225385443e-05, + "loss": 3.6619, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882621630634391e-05, + "loss": 3.6626, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881783035883339e-05, + "loss": 3.6595, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.8809460790126596e-05, + "loss": 3.6573, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8801074842616076e-05, + "loss": 3.6482, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792688895105556e-05, + "loss": 3.6585, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8784302947595036e-05, + "loss": 3.666, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8775933378888245e-05, + "loss": 3.6698, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.8767547431377725e-05, + "loss": 3.6502, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8759161483867205e-05, + "loss": 3.6541, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.847038745880127, + "eval_runtime": 322.988, + "eval_samples_per_second": 1181.44, + "eval_steps_per_second": 36.921, + "step": 686871 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750775536356685e-05, + "loss": 3.6662, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742389588846165e-05, + "loss": 3.6581, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8734003641335645e-05, + "loss": 3.6568, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.8725617693825125e-05, + "loss": 3.6551, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871723174631461e-05, + "loss": 3.648, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870887855641155e-05, + "loss": 3.6469, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870049260890103e-05, + "loss": 3.6439, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869210666139051e-05, + "loss": 3.6479, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868372071387999e-05, + "loss": 3.6484, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.86753511451732e-05, + "loss": 3.6616, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866698157646641e-05, + "loss": 3.6519, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865859562895589e-05, + "loss": 3.6494, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865020968144537e-05, + "loss": 3.6593, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864182373393485e-05, + "loss": 3.6475, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8633437786424334e-05, + "loss": 3.654, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8625051838913814e-05, + "loss": 3.6353, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616665891403294e-05, + "loss": 3.6404, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8608279943892774e-05, + "loss": 3.6567, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599893996382254e-05, + "loss": 3.6485, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8591524427675463e-05, + "loss": 3.6627, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858313848016494e-05, + "loss": 3.6458, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857475253265442e-05, + "loss": 3.6634, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.85663665851439e-05, + "loss": 3.6476, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855799701643711e-05, + "loss": 3.6477, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854961106892659e-05, + "loss": 3.6505, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854122512141607e-05, + "loss": 3.6495, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853283917390555e-05, + "loss": 3.6569, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852446960519877e-05, + "loss": 3.6454, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851608365768825e-05, + "loss": 3.6546, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850769771017773e-05, + "loss": 3.6463, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849931176266721e-05, + "loss": 3.6323, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849094219396042e-05, + "loss": 3.6549, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.84825562464499e-05, + "loss": 3.6517, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847417029893938e-05, + "loss": 3.6529, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846578435142886e-05, + "loss": 3.6503, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8457414782722066e-05, + "loss": 3.645, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.8449028835211546e-05, + "loss": 3.6493, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.8440642887701026e-05, + "loss": 3.6537, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.8432256940190506e-05, + "loss": 3.6544, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842388737148372e-05, + "loss": 3.6324, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.84155014239732e-05, + "loss": 3.6423, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840711547646268e-05, + "loss": 3.6388, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839872952895216e-05, + "loss": 3.6478, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839034358144164e-05, + "loss": 3.6546, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838197401273485e-05, + "loss": 3.6405, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837358806522433e-05, + "loss": 3.6562, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836520211771381e-05, + "loss": 3.6427, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835681617020329e-05, + "loss": 3.6565, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.83484466014965e-05, + "loss": 3.6434, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.834006065398598e-05, + "loss": 3.6347, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833167470647546e-05, + "loss": 3.6433, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832328875896494e-05, + "loss": 3.6326, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831490281145442e-05, + "loss": 3.65, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8306533242747635e-05, + "loss": 3.6382, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8298147295237115e-05, + "loss": 3.6435, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8289761347726595e-05, + "loss": 3.6277, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828137540021607e-05, + "loss": 3.6445, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.8273005831509284e-05, + "loss": 3.6311, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.8264619883998764e-05, + "loss": 3.6487, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.8256233936488244e-05, + "loss": 3.6358, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824784798897772e-05, + "loss": 3.6389, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823947842027093e-05, + "loss": 3.6365, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823109247276041e-05, + "loss": 3.6288, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822270652524989e-05, + "loss": 3.6481, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821432057773937e-05, + "loss": 3.6359, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820595100903259e-05, + "loss": 3.6464, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819756506152207e-05, + "loss": 3.6317, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818917911401154e-05, + "loss": 3.6316, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818079316650102e-05, + "loss": 3.6296, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.81724072189905e-05, + "loss": 3.6384, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816403765028371e-05, + "loss": 3.6363, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815565170277319e-05, + "loss": 3.6409, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814726575526267e-05, + "loss": 3.641, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813887980775215e-05, + "loss": 3.661, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.813051023904537e-05, + "loss": 3.6473, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812212429153485e-05, + "loss": 3.6421, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811373834402433e-05, + "loss": 3.6422, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810535239651381e-05, + "loss": 3.6308, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809696644900329e-05, + "loss": 3.6326, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.8088596880296496e-05, + "loss": 3.6499, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.8080210932785976e-05, + "loss": 3.6504, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071824985275456e-05, + "loss": 3.6393, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.8063439037764936e-05, + "loss": 3.625, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.8055069469058145e-05, + "loss": 3.6391, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.8046683521547625e-05, + "loss": 3.6211, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8038297574037105e-05, + "loss": 3.6367, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029911626526585e-05, + "loss": 3.6351, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.80215420578198e-05, + "loss": 3.6346, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801315611030928e-05, + "loss": 3.6478, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800477016279876e-05, + "loss": 3.6427, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799638421528824e-05, + "loss": 3.6327, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798801464658145e-05, + "loss": 3.6339, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797962869907093e-05, + "loss": 3.6389, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797124275156041e-05, + "loss": 3.6296, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796285680404989e-05, + "loss": 3.63, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795447085653937e-05, + "loss": 3.6394, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794610128783258e-05, + "loss": 3.646, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793771534032206e-05, + "loss": 3.6571, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792932939281154e-05, + "loss": 3.6338, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792094344530102e-05, + "loss": 3.6458, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7912557497790505e-05, + "loss": 3.6338, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7904187929083714e-05, + "loss": 3.6386, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895801981573194e-05, + "loss": 3.6403, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.7887416034062674e-05, + "loss": 3.6419, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7879030086552154e-05, + "loss": 3.6476, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787066051784536e-05, + "loss": 3.6255, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786227457033484e-05, + "loss": 3.6268, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785388862282432e-05, + "loss": 3.6234, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.78455026753138e-05, + "loss": 3.6297, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783713310660701e-05, + "loss": 3.6391, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782874715909649e-05, + "loss": 3.6397, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782036121158597e-05, + "loss": 3.6161, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781197526407546e-05, + "loss": 3.6403, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780358931656494e-05, + "loss": 3.6444, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779521974785815e-05, + "loss": 3.6398, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778683380034763e-05, + "loss": 3.6417, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777844785283711e-05, + "loss": 3.6361, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777006190532659e-05, + "loss": 3.6275, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776167595781607e-05, + "loss": 3.6419, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775330638910928e-05, + "loss": 3.6414, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.7744920441598757e-05, + "loss": 3.6324, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.7736534494088237e-05, + "loss": 3.6193, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.7728148546577716e-05, + "loss": 3.6334, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719778977870926e-05, + "loss": 3.6329, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771139303036041e-05, + "loss": 3.6361, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770300708284989e-05, + "loss": 3.6365, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769462113533937e-05, + "loss": 3.6408, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768623518782885e-05, + "loss": 3.6263, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767786561912206e-05, + "loss": 3.6504, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766947967161154e-05, + "loss": 3.6288, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766109372410102e-05, + "loss": 3.6385, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.7652707776590494e-05, + "loss": 3.6479, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764433820788371e-05, + "loss": 3.6368, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763595226037319e-05, + "loss": 3.6426, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762756631286267e-05, + "loss": 3.6406, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761918036535215e-05, + "loss": 3.6233, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610810796645366e-05, + "loss": 3.6322, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.7602424849134846e-05, + "loss": 3.6291, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.7594038901624326e-05, + "loss": 3.6431, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.75856529541138e-05, + "loss": 3.6399, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7577283385407015e-05, + "loss": 3.6395, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568897437896495e-05, + "loss": 3.6392, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756051149038597e-05, + "loss": 3.6328, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755212554287545e-05, + "loss": 3.6238, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7543755974168664e-05, + "loss": 3.6348, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7535370026658144e-05, + "loss": 3.6432, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752698407914762e-05, + "loss": 3.6432, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.7518598131637104e-05, + "loss": 3.6262, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751022856293032e-05, + "loss": 3.631, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.843494415283203, + "eval_runtime": 315.4645, + "eval_samples_per_second": 1209.616, + "eval_steps_per_second": 37.801, + "step": 763190 + }, + { + "epoch": 0.0, + "learning_rate": 3.750184261541979e-05, + "loss": 3.6252, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749345666790927e-05, + "loss": 3.6309, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748507072039875e-05, + "loss": 3.638, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747668477288823e-05, + "loss": 3.6399, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746831520418144e-05, + "loss": 3.6461, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745992925667092e-05, + "loss": 3.634, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.74515433091604e-05, + "loss": 3.6389, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744315736164988e-05, + "loss": 3.6336, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743478779294309e-05, + "loss": 3.6304, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742640184543257e-05, + "loss": 3.6306, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741801589792206e-05, + "loss": 3.6403, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740962995041154e-05, + "loss": 3.6419, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.7401260381704747e-05, + "loss": 3.6384, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7392874434194226e-05, + "loss": 3.612, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.7384488486683706e-05, + "loss": 3.6368, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.7376102539173186e-05, + "loss": 3.6191, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.7367716591662666e-05, + "loss": 3.6293, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7359330644152146e-05, + "loss": 3.6296, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.7350944696641626e-05, + "loss": 3.631, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7342558749131106e-05, + "loss": 3.6403, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7334189180424315e-05, + "loss": 3.6444, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7325803232913795e-05, + "loss": 3.6373, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7317417285403275e-05, + "loss": 3.6307, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7309031337892755e-05, + "loss": 3.6256, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730066176918597e-05, + "loss": 3.6371, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729227582167545e-05, + "loss": 3.6343, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728388987416493e-05, + "loss": 3.6304, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727550392665441e-05, + "loss": 3.6282, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726713435794762e-05, + "loss": 3.6257, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.72587484104371e-05, + "loss": 3.6324, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725036246292658e-05, + "loss": 3.6172, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724197651541606e-05, + "loss": 3.6397, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723359056790554e-05, + "loss": 3.6394, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722522099919875e-05, + "loss": 3.6365, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721683505168823e-05, + "loss": 3.6287, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720844910417771e-05, + "loss": 3.6291, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.720006315666719e-05, + "loss": 3.6352, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191693587960405e-05, + "loss": 3.6281, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7183307640449885e-05, + "loss": 3.6202, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174921692939365e-05, + "loss": 3.6207, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7166535745428845e-05, + "loss": 3.6222, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.7158166176722054e-05, + "loss": 3.6269, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7149780229211534e-05, + "loss": 3.6277, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.7141394281701014e-05, + "loss": 3.6298, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.7133008334190493e-05, + "loss": 3.6375, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.71246387654837e-05, + "loss": 3.6269, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711625281797318e-05, + "loss": 3.6318, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710786687046266e-05, + "loss": 3.6315, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709948092295214e-05, + "loss": 3.604, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709109497544163e-05, + "loss": 3.6406, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708272540673484e-05, + "loss": 3.6225, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707433945922432e-05, + "loss": 3.6279, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.70659535117138e-05, + "loss": 3.6313, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705756756420328e-05, + "loss": 3.6235, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704919799549649e-05, + "loss": 3.609, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704081204798597e-05, + "loss": 3.6209, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703242610047545e-05, + "loss": 3.6211, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702404015296493e-05, + "loss": 3.6205, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7015670584258136e-05, + "loss": 3.6346, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.7007284636747616e-05, + "loss": 3.6217, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6998898689237096e-05, + "loss": 3.6174, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6990512741726576e-05, + "loss": 3.6407, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698214317301979e-05, + "loss": 3.6119, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697375722550927e-05, + "loss": 3.6116, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696537127799875e-05, + "loss": 3.6252, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6956985330488225e-05, + "loss": 3.6192, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694861576178144e-05, + "loss": 3.6163, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694022981427092e-05, + "loss": 3.6235, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.69318438667604e-05, + "loss": 3.6067, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923457919249874e-05, + "loss": 3.6135, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691508835054309e-05, + "loss": 3.6338, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690670240303257e-05, + "loss": 3.6187, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689831645552205e-05, + "loss": 3.6319, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688993050801153e-05, + "loss": 3.6222, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688154456050101e-05, + "loss": 3.6378, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6873174991794226e-05, + "loss": 3.6155, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.68647890442837e-05, + "loss": 3.6307, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685640309677318e-05, + "loss": 3.6258, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684801714926266e-05, + "loss": 3.6082, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683964758055587e-05, + "loss": 3.6341, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683126163304535e-05, + "loss": 3.6268, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682287568553483e-05, + "loss": 3.6256, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681448973802431e-05, + "loss": 3.6274, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.6806120169317523e-05, + "loss": 3.6081, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.6797734221807003e-05, + "loss": 3.6059, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.6789348274296483e-05, + "loss": 3.6153, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678096232678596e-05, + "loss": 3.6267, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677259275807917e-05, + "loss": 3.616, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676420681056865e-05, + "loss": 3.6137, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675582086305813e-05, + "loss": 3.6184, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674743491554761e-05, + "loss": 3.6227, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673904896803709e-05, + "loss": 3.6161, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.67306793993303e-05, + "loss": 3.6135, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672229345181978e-05, + "loss": 3.6334, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671390750430926e-05, + "loss": 3.6359, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670552155679874e-05, + "loss": 3.6269, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669715198809196e-05, + "loss": 3.6105, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668876604058144e-05, + "loss": 3.6204, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668038009307092e-05, + "loss": 3.6167, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.66719941455604e-05, + "loss": 3.6313, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.6663624576853606e-05, + "loss": 3.6192, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.6655238629343086e-05, + "loss": 3.6192, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.6646852681832566e-05, + "loss": 3.6152, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6638466734322046e-05, + "loss": 3.6276, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6630097165615255e-05, + "loss": 3.6164, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6621711218104735e-05, + "loss": 3.6181, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6613325270594215e-05, + "loss": 3.609, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604939323083695e-05, + "loss": 3.6155, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659656975437691e-05, + "loss": 3.612, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658818380686639e-05, + "loss": 3.6091, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657979785935587e-05, + "loss": 3.6157, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657141191184535e-05, + "loss": 3.6156, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656304234313856e-05, + "loss": 3.6214, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655465639562804e-05, + "loss": 3.612, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654627044811752e-05, + "loss": 3.6242, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.6537884500607e-05, + "loss": 3.6305, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652949855309648e-05, + "loss": 3.6188, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652112898438969e-05, + "loss": 3.6324, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651274303687917e-05, + "loss": 3.6115, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650435708936865e-05, + "loss": 3.6156, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649597114185813e-05, + "loss": 3.6121, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.6487601573151344e-05, + "loss": 3.6083, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6479215625640824e-05, + "loss": 3.6186, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6470829678130304e-05, + "loss": 3.6167, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6462443730619784e-05, + "loss": 3.6198, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645407416191299e-05, + "loss": 3.6146, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644568821440247e-05, + "loss": 3.6234, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643730226689195e-05, + "loss": 3.6147, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642891631938143e-05, + "loss": 3.6126, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642054675067464e-05, + "loss": 3.6202, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641216080316412e-05, + "loss": 3.6214, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.64037748556536e-05, + "loss": 3.6294, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639538890814308e-05, + "loss": 3.6131, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.63870193394363e-05, + "loss": 3.6308, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637863339192578e-05, + "loss": 3.6159, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637024744441526e-05, + "loss": 3.6242, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636186149690474e-05, + "loss": 3.6233, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635349192819795e-05, + "loss": 3.61, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634510598068743e-05, + "loss": 3.6113, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633672003317691e-05, + "loss": 3.63, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632833408566639e-05, + "loss": 3.6078, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6319964516959596e-05, + "loss": 3.6217, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6311578569449076e-05, + "loss": 3.6202, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.6303192621938556e-05, + "loss": 3.619, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6294806674428036e-05, + "loss": 3.6126, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628643710572125e-05, + "loss": 3.6208, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627805115821073e-05, + "loss": 3.6209, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626966521070021e-05, + "loss": 3.6201, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626127926318969e-05, + "loss": 3.619, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.837454080581665, + "eval_runtime": 301.7161, + "eval_samples_per_second": 1264.735, + "eval_steps_per_second": 39.524, + "step": 839510 + }, + { + "epoch": 1.0, + "learning_rate": 3.62529096944829e-05, + "loss": 3.6054, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624452374697238e-05, + "loss": 3.6111, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623613779946186e-05, + "loss": 3.6146, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622775185195134e-05, + "loss": 3.6155, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.621936590444082e-05, + "loss": 3.6263, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621099633573403e-05, + "loss": 3.6102, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620261038822351e-05, + "loss": 3.6157, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619422444071299e-05, + "loss": 3.6123, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6185838493202476e-05, + "loss": 3.605, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.6177468924495685e-05, + "loss": 3.6043, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.6169082976985165e-05, + "loss": 3.6179, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.6160697029474645e-05, + "loss": 3.623, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.6152327460767854e-05, + "loss": 3.6143, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6143941513257334e-05, + "loss": 3.5905, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6135555565746814e-05, + "loss": 3.6125, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.6127169618236294e-05, + "loss": 3.596, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.6118783670725774e-05, + "loss": 3.6063, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611039772321525e-05, + "loss": 3.6076, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610201177570473e-05, + "loss": 3.6101, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.6093625828194214e-05, + "loss": 3.6137, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608525625948742e-05, + "loss": 3.622, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.60768703119769e-05, + "loss": 3.6132, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606848436446638e-05, + "loss": 3.6097, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.606009841695586e-05, + "loss": 3.6012, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605172884824907e-05, + "loss": 3.6144, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604334290073855e-05, + "loss": 3.6118, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603495695322803e-05, + "loss": 3.6053, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602657100571751e-05, + "loss": 3.6062, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601820143701072e-05, + "loss": 3.6025, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.60098154895002e-05, + "loss": 3.6083, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600142954198968e-05, + "loss": 3.6006, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599304359447917e-05, + "loss": 3.6091, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598467402577238e-05, + "loss": 3.615, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597628807826186e-05, + "loss": 3.6138, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596790213075134e-05, + "loss": 3.6091, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595951618324082e-05, + "loss": 3.6074, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.5951146614534026e-05, + "loss": 3.6157, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.5942760667023506e-05, + "loss": 3.6016, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.5934374719512986e-05, + "loss": 3.5997, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.5925988772002466e-05, + "loss": 3.6035, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.5917619203295675e-05, + "loss": 3.595, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5909233255785155e-05, + "loss": 3.603, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5900847308274635e-05, + "loss": 3.6044, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589246136076412e-05, + "loss": 3.6082, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588409179205733e-05, + "loss": 3.611, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587570584454681e-05, + "loss": 3.6125, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586731989703629e-05, + "loss": 3.6104, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585893394952577e-05, + "loss": 3.6067, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.585056438081898e-05, + "loss": 3.5842, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584217843330846e-05, + "loss": 3.6153, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583379248579794e-05, + "loss": 3.6014, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582540653828742e-05, + "loss": 3.603, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581703696958063e-05, + "loss": 3.6102, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580865102207011e-05, + "loss": 3.6029, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580026507455959e-05, + "loss": 3.5849, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579187912704907e-05, + "loss": 3.5953, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5783509558342284e-05, + "loss": 3.6027, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.5775123610831764e-05, + "loss": 3.595, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5766737663321244e-05, + "loss": 3.6153, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.5758351715810724e-05, + "loss": 3.6003, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574998214710393e-05, + "loss": 3.5904, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574159619959341e-05, + "loss": 3.6158, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573321025208289e-05, + "loss": 3.5941, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572482430457237e-05, + "loss": 3.5885, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571645473586558e-05, + "loss": 3.6026, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570806878835506e-05, + "loss": 3.5963, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569968284084454e-05, + "loss": 3.5954, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569129689333402e-05, + "loss": 3.5986, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568291094582351e-05, + "loss": 3.5856, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567454137711672e-05, + "loss": 3.593, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.56661554296062e-05, + "loss": 3.6075, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565776948209568e-05, + "loss": 3.5998, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564938353458516e-05, + "loss": 3.6107, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564101396587837e-05, + "loss": 3.6001, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563262801836785e-05, + "loss": 3.6171, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562424207085733e-05, + "loss": 3.5951, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5615856123346807e-05, + "loss": 3.6093, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5607486554640016e-05, + "loss": 3.6008, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5599100607129496e-05, + "loss": 3.5879, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5590714659618976e-05, + "loss": 3.6089, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558232871210846e-05, + "loss": 3.6089, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557395914340167e-05, + "loss": 3.6043, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556557319589115e-05, + "loss": 3.6077, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555718724838063e-05, + "loss": 3.5868, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554880130087011e-05, + "loss": 3.5834, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554043173216332e-05, + "loss": 3.5936, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.55320457846528e-05, + "loss": 3.6046, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552365983714228e-05, + "loss": 3.5942, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551527388963176e-05, + "loss": 3.5927, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550690432092497e-05, + "loss": 3.5951, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549851837341445e-05, + "loss": 3.5981, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549013242590393e-05, + "loss": 3.5951, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.5481746478393416e-05, + "loss": 3.5961, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473376909686625e-05, + "loss": 3.6054, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5464990962176105e-05, + "loss": 3.618, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5456605014665585e-05, + "loss": 3.6055, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5448219067155065e-05, + "loss": 3.5918, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5439849498448274e-05, + "loss": 3.5939, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5431463550937754e-05, + "loss": 3.5983, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.5423077603427234e-05, + "loss": 3.6092, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.5414691655916714e-05, + "loss": 3.5991, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540632208720992e-05, + "loss": 3.5982, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.53979361396994e-05, + "loss": 3.5959, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538955019218888e-05, + "loss": 3.6019, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538116424467837e-05, + "loss": 3.6021, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537279467597158e-05, + "loss": 3.5938, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536440872846106e-05, + "loss": 3.5891, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535602278095054e-05, + "loss": 3.5924, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534763683344002e-05, + "loss": 3.5951, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533926726473323e-05, + "loss": 3.5874, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533088131722271e-05, + "loss": 3.5942, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532249536971219e-05, + "loss": 3.5909, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.53141258010054e-05, + "loss": 3.5977, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530573985349488e-05, + "loss": 3.5909, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529735390598436e-05, + "loss": 3.6063, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528896795847384e-05, + "loss": 3.6103, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528058201096332e-05, + "loss": 3.5955, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527221244225653e-05, + "loss": 3.6083, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526382649474601e-05, + "loss": 3.5976, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525544054723549e-05, + "loss": 3.5934, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524705459972497e-05, + "loss": 3.5935, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523868503101818e-05, + "loss": 3.5839, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523029908350766e-05, + "loss": 3.5961, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522191313599714e-05, + "loss": 3.5988, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521352718848662e-05, + "loss": 3.601, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520515761977983e-05, + "loss": 3.5928, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519677167226931e-05, + "loss": 3.6015, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518838572475879e-05, + "loss": 3.5959, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517999977724828e-05, + "loss": 3.5931, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.5171630208541486e-05, + "loss": 3.5977, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5163244261030966e-05, + "loss": 3.6024, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5154858313520446e-05, + "loss": 3.6063, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514647236600992e-05, + "loss": 3.5886, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5138102797303135e-05, + "loss": 3.6107, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5129716849792615e-05, + "loss": 3.5914, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5121330902282095e-05, + "loss": 3.6044, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511294495477157e-05, + "loss": 3.6027, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5104575386064784e-05, + "loss": 3.5934, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5096189438554264e-05, + "loss": 3.5878, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.5087803491043744e-05, + "loss": 3.6113, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.5079417543533224e-05, + "loss": 3.5841, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507104797482644e-05, + "loss": 3.6027, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506266202731592e-05, + "loss": 3.596, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505427607980539e-05, + "loss": 3.599, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504589013229487e-05, + "loss": 3.5936, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503752056358809e-05, + "loss": 3.598, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502913461607757e-05, + "loss": 3.5964, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502074866856704e-05, + "loss": 3.6038, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501236272105652e-05, + "loss": 3.5952, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.8385751247406006, + "eval_runtime": 302.3664, + "eval_samples_per_second": 1262.015, + "eval_steps_per_second": 39.439, + "step": 915830 + }, + { + "epoch": 0.0, + "learning_rate": 3.500399315234974e-05, + "loss": 3.5855, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499560720483922e-05, + "loss": 3.5891, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.49872212573287e-05, + "loss": 3.5949, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497883530981818e-05, + "loss": 3.599, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970465741111393e-05, + "loss": 3.601, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496207979360087e-05, + "loss": 3.5907, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4953693846090347e-05, + "loss": 3.5964, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4945307898579827e-05, + "loss": 3.5922, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493693832987304e-05, + "loss": 3.5858, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.4928552382362516e-05, + "loss": 3.5805, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4920166434851996e-05, + "loss": 3.6012, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4911780487341476e-05, + "loss": 3.6014, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490341091863469e-05, + "loss": 3.5938, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489502497112417e-05, + "loss": 3.5721, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488663902361365e-05, + "loss": 3.5909, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487825307610313e-05, + "loss": 3.5748, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486988350739634e-05, + "loss": 3.5901, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486149755988582e-05, + "loss": 3.5891, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.48531116123753e-05, + "loss": 3.5869, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484472566486478e-05, + "loss": 3.5955, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483633971735426e-05, + "loss": 3.5984, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482797014864747e-05, + "loss": 3.5883, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481958420113695e-05, + "loss": 3.5895, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481119825362643e-05, + "loss": 3.5866, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480281230611591e-05, + "loss": 3.5943, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4794442737409125e-05, + "loss": 3.5913, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4786056789898605e-05, + "loss": 3.5822, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4777670842388085e-05, + "loss": 3.5864, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4769284894877565e-05, + "loss": 3.5863, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760915326170774e-05, + "loss": 3.5859, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4752529378660254e-05, + "loss": 3.5841, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4744143431149734e-05, + "loss": 3.5919, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4735757483639214e-05, + "loss": 3.5909, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472738791493242e-05, + "loss": 3.5986, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.47190019674219e-05, + "loss": 3.586, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471061601991138e-05, + "loss": 3.5862, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470223007240086e-05, + "loss": 3.5973, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469386050369408e-05, + "loss": 3.5795, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468547455618356e-05, + "loss": 3.581, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467708860867304e-05, + "loss": 3.5816, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466870266116252e-05, + "loss": 3.58, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466033309245573e-05, + "loss": 3.5808, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465194714494521e-05, + "loss": 3.585, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464356119743469e-05, + "loss": 3.5911, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463517524992417e-05, + "loss": 3.5898, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4626805681217377e-05, + "loss": 3.5909, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.4618419733706857e-05, + "loss": 3.589, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4610033786196337e-05, + "loss": 3.5909, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4601647838685816e-05, + "loss": 3.5667, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459327826997903e-05, + "loss": 3.5938, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458489232246851e-05, + "loss": 3.5814, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457650637495799e-05, + "loss": 3.5821, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456812042744747e-05, + "loss": 3.5886, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455975085874068e-05, + "loss": 3.5828, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455136491123016e-05, + "loss": 3.5673, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454297896371964e-05, + "loss": 3.5781, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453459301620912e-05, + "loss": 3.5839, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452622344750233e-05, + "loss": 3.5749, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451783749999181e-05, + "loss": 3.5945, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450945155248129e-05, + "loss": 3.5849, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450106560497077e-05, + "loss": 3.5692, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.4492696036263986e-05, + "loss": 3.598, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.4484310088753466e-05, + "loss": 3.5729, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.4475924141242946e-05, + "loss": 3.5713, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.4467538193732426e-05, + "loss": 3.5842, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4459168625025635e-05, + "loss": 3.5757, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4450782677515115e-05, + "loss": 3.5741, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.4442396730004595e-05, + "loss": 3.5814, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.4434010782494075e-05, + "loss": 3.5686, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.4425641213787284e-05, + "loss": 3.5693, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4417255266276764e-05, + "loss": 3.5903, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4408869318766244e-05, + "loss": 3.5834, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4400483371255724e-05, + "loss": 3.5881, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4392097423745204e-05, + "loss": 3.5845, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438372785503842e-05, + "loss": 3.5954, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.43753419075279e-05, + "loss": 3.5729, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436695596001738e-05, + "loss": 3.5939, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435858639131059e-05, + "loss": 3.5794, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435020044380007e-05, + "loss": 3.5731, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434181449628955e-05, + "loss": 3.5856, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433342854877903e-05, + "loss": 3.5926, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432504260126851e-05, + "loss": 3.5833, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431667303256172e-05, + "loss": 3.5914, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.43082870850512e-05, + "loss": 3.5648, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429990113754068e-05, + "loss": 3.5638, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429151519003016e-05, + "loss": 3.5732, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428314562132337e-05, + "loss": 3.5841, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427475967381285e-05, + "loss": 3.5786, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426637372630233e-05, + "loss": 3.5734, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425798777879181e-05, + "loss": 3.5767, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424961821008502e-05, + "loss": 3.5782, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.42412322625745e-05, + "loss": 3.5736, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423284631506398e-05, + "loss": 3.5759, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422446036755346e-05, + "loss": 3.5864, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421609079884667e-05, + "loss": 3.5951, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420770485133615e-05, + "loss": 3.5864, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419931890382563e-05, + "loss": 3.5722, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419093295631511e-05, + "loss": 3.5781, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418256338760833e-05, + "loss": 3.5772, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417417744009781e-05, + "loss": 3.5886, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416579149258729e-05, + "loss": 3.5854, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415740554507677e-05, + "loss": 3.5769, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4149035976369976e-05, + "loss": 3.5777, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4140650028859456e-05, + "loss": 3.5805, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4132264081348936e-05, + "loss": 3.5806, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4123878133838416e-05, + "loss": 3.5752, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.4115508565131625e-05, + "loss": 3.5731, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4107122617621105e-05, + "loss": 3.5722, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.4098736670110585e-05, + "loss": 3.5749, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4090350722600065e-05, + "loss": 3.5718, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408198115389328e-05, + "loss": 3.5726, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407359520638276e-05, + "loss": 3.572, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406520925887224e-05, + "loss": 3.5795, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4056823311361714e-05, + "loss": 3.5709, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404845374265493e-05, + "loss": 3.5856, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.404006779514441e-05, + "loss": 3.5927, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403168184763389e-05, + "loss": 3.5771, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402329590012336e-05, + "loss": 3.5865, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401492633141658e-05, + "loss": 3.5811, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400654038390606e-05, + "loss": 3.5747, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399815443639554e-05, + "loss": 3.5792, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398976848888502e-05, + "loss": 3.5615, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.39813825413745e-05, + "loss": 3.5787, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.3973012972667714e-05, + "loss": 3.5765, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396462702515719e-05, + "loss": 3.5838, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395624107764667e-05, + "loss": 3.5751, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394785513013615e-05, + "loss": 3.5844, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393948556142936e-05, + "loss": 3.5765, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3931099613918836e-05, + "loss": 3.5717, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3922713666408316e-05, + "loss": 3.5826, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391434409770153e-05, + "loss": 3.5788, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390595815019101e-05, + "loss": 3.589, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897572202680485e-05, + "loss": 3.5736, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388918625516997e-05, + "loss": 3.5902, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388081668646319e-05, + "loss": 3.5757, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387243073895266e-05, + "loss": 3.5819, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386404479144214e-05, + "loss": 3.5852, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385565884393162e-05, + "loss": 3.574, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.38472728964211e-05, + "loss": 3.57, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383890332771431e-05, + "loss": 3.5897, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383051738020379e-05, + "loss": 3.5689, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382213143269327e-05, + "loss": 3.5794, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381374548518275e-05, + "loss": 3.5796, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380537591647596e-05, + "loss": 3.5804, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379698996896544e-05, + "loss": 3.5775, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.3788604021454926e-05, + "loss": 3.5762, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3780218073944406e-05, + "loss": 3.5797, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3771848505237615e-05, + "loss": 3.5804, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3763462557727095e-05, + "loss": 3.5789, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.838780403137207, + "eval_runtime": 360.8663, + "eval_samples_per_second": 1057.43, + "eval_steps_per_second": 33.045, + "step": 992150 + }, + { + "epoch": 1.0, + "learning_rate": 3.3755076610216575e-05, + "loss": 3.5713, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.3746690662706055e-05, + "loss": 3.5665, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.3738321093999264e-05, + "loss": 3.5746, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.3729935146488744e-05, + "loss": 3.5857, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3721549198978224e-05, + "loss": 3.5779, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.3713163251467704e-05, + "loss": 3.5744, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370479368276091e-05, + "loss": 3.5784, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369640773525039e-05, + "loss": 3.5732, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368802178773988e-05, + "loss": 3.5651, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367963584022936e-05, + "loss": 3.5672, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367126627152257e-05, + "loss": 3.5811, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366288032401205e-05, + "loss": 3.5804, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365451075530526e-05, + "loss": 3.5828, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364612480779474e-05, + "loss": 3.5486, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363773886028422e-05, + "loss": 3.5701, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.36293529127737e-05, + "loss": 3.5592, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362096696526318e-05, + "loss": 3.5734, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361258101775266e-05, + "loss": 3.569, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360419507024214e-05, + "loss": 3.5695, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359580912273162e-05, + "loss": 3.5732, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358743955402483e-05, + "loss": 3.587, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357905360651431e-05, + "loss": 3.5727, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357066765900379e-05, + "loss": 3.5702, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356228171149327e-05, + "loss": 3.5671, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355391214278648e-05, + "loss": 3.5772, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354552619527596e-05, + "loss": 3.5716, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353714024776544e-05, + "loss": 3.5647, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352875430025492e-05, + "loss": 3.5703, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.352038473154813e-05, + "loss": 3.5644, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351199878403761e-05, + "loss": 3.5662, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350361283652709e-05, + "loss": 3.5676, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349522688901657e-05, + "loss": 3.5712, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348685732030979e-05, + "loss": 3.5711, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347847137279927e-05, + "loss": 3.579, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.347008542528875e-05, + "loss": 3.5708, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346169947777823e-05, + "loss": 3.5706, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3453329909071436e-05, + "loss": 3.5784, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3444943961560916e-05, + "loss": 3.559, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.3436558014050396e-05, + "loss": 3.5639, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.3428172066539876e-05, + "loss": 3.5654, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.3419786119029356e-05, + "loss": 3.5592, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.3411416550322565e-05, + "loss": 3.5661, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.3403030602812045e-05, + "loss": 3.5683, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.3394644655301525e-05, + "loss": 3.5716, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.3386258707791004e-05, + "loss": 3.5717, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337788913908422e-05, + "loss": 3.5716, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.33695031915737e-05, + "loss": 3.573, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336111724406318e-05, + "loss": 3.5673, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335273129655266e-05, + "loss": 3.5512, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334436172784587e-05, + "loss": 3.573, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333597578033535e-05, + "loss": 3.5687, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332758983282483e-05, + "loss": 3.567, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331920388531431e-05, + "loss": 3.5698, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331083431660752e-05, + "loss": 3.5625, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.3302448369097e-05, + "loss": 3.5522, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329406242158648e-05, + "loss": 3.557, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328567647407596e-05, + "loss": 3.5687, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.3277306905369174e-05, + "loss": 3.5542, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.3268920957858654e-05, + "loss": 3.58, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.3260535010348134e-05, + "loss": 3.5691, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.3252149062837614e-05, + "loss": 3.547, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324377949413082e-05, + "loss": 3.5771, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.32353935466203e-05, + "loss": 3.5584, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322700759910978e-05, + "loss": 3.5562, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321862165159926e-05, + "loss": 3.5606, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.321025208289247e-05, + "loss": 3.5643, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320186613538195e-05, + "loss": 3.5544, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319348018787143e-05, + "loss": 3.5657, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318509424036091e-05, + "loss": 3.5467, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317672467165413e-05, + "loss": 3.5536, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316833872414361e-05, + "loss": 3.5721, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315995277663309e-05, + "loss": 3.5619, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315156682912257e-05, + "loss": 3.5726, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314319726041578e-05, + "loss": 3.5621, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313481131290526e-05, + "loss": 3.5776, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.3126425365394737e-05, + "loss": 3.5573, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311803941788421e-05, + "loss": 3.5769, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3109669849177426e-05, + "loss": 3.5596, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3101283901666906e-05, + "loss": 3.5577, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.3092897954156386e-05, + "loss": 3.5652, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.3084512006645866e-05, + "loss": 3.5808, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307614243793908e-05, + "loss": 3.5618, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306775649042856e-05, + "loss": 3.5738, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305937054291804e-05, + "loss": 3.5461, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3050984595407514e-05, + "loss": 3.5498, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304261502670073e-05, + "loss": 3.5564, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303422907919021e-05, + "loss": 3.5641, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.3025843131679683e-05, + "loss": 3.56, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.3017457184169163e-05, + "loss": 3.5609, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300908761546238e-05, + "loss": 3.5577, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300070166795186e-05, + "loss": 3.5593, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299231572044133e-05, + "loss": 3.5606, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298392977293082e-05, + "loss": 3.5577, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.2975560204224035e-05, + "loss": 3.5674, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296717425671351e-05, + "loss": 3.5787, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295878830920299e-05, + "loss": 3.5736, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295040236169247e-05, + "loss": 3.5543, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.2942032792985684e-05, + "loss": 3.5604, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293364684547516e-05, + "loss": 3.5607, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292526089796464e-05, + "loss": 3.5709, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291687495045412e-05, + "loss": 3.5646, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290850538174733e-05, + "loss": 3.5621, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.2900119434236806e-05, + "loss": 3.5609, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2891733486726286e-05, + "loss": 3.5675, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288334753921577e-05, + "loss": 3.5627, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287497797050898e-05, + "loss": 3.5578, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286659202299846e-05, + "loss": 3.5566, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285820607548794e-05, + "loss": 3.5521, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284982012797742e-05, + "loss": 3.5598, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284145055927063e-05, + "loss": 3.552, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283306461176011e-05, + "loss": 3.556, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282467866424959e-05, + "loss": 3.5547, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281629271673907e-05, + "loss": 3.5622, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280792314803228e-05, + "loss": 3.5552, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279953720052176e-05, + "loss": 3.5656, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279115125301124e-05, + "loss": 3.5733, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.2782765305500727e-05, + "loss": 3.5653, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.2774395736793936e-05, + "loss": 3.5696, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.2766009789283416e-05, + "loss": 3.5647, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.2757623841772896e-05, + "loss": 3.556, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2749237894262375e-05, + "loss": 3.5629, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.2740868325555585e-05, + "loss": 3.5468, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.2732482378045065e-05, + "loss": 3.5613, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2724096430534544e-05, + "loss": 3.5531, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.2715710483024024e-05, + "loss": 3.5656, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2707340914317234e-05, + "loss": 3.5621, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.2698954966806713e-05, + "loss": 3.564, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.2690569019296193e-05, + "loss": 3.5553, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268218307178568e-05, + "loss": 3.5565, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267381350307889e-05, + "loss": 3.5622, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266542755556837e-05, + "loss": 3.5639, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265704160805785e-05, + "loss": 3.5718, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264865566054733e-05, + "loss": 3.5561, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.264028609184054e-05, + "loss": 3.5726, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263190014433002e-05, + "loss": 3.5585, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.26235141968195e-05, + "loss": 3.5621, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261512824930898e-05, + "loss": 3.5671, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260675868060219e-05, + "loss": 3.5573, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259837273309167e-05, + "loss": 3.5563, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258998678558115e-05, + "loss": 3.5709, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2581600838070634e-05, + "loss": 3.5572, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257323126936384e-05, + "loss": 3.5576, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256484532185332e-05, + "loss": 3.5654, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.25564593743428e-05, + "loss": 3.5645, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254807342683228e-05, + "loss": 3.5585, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253970385812549e-05, + "loss": 3.5617, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253131791061497e-05, + "loss": 3.5587, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252293196310445e-05, + "loss": 3.568, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251454601559393e-05, + "loss": 3.557, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.8406033515930176, + "eval_runtime": 303.3328, + "eval_samples_per_second": 1257.994, + "eval_steps_per_second": 39.313, + "step": 1068470 + }, + { + "epoch": 0.0, + "learning_rate": 3.250617644688714e-05, + "loss": 3.552, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249779049937662e-05, + "loss": 3.5496, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.24894045518661e-05, + "loss": 3.5589, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248101860435559e-05, + "loss": 3.57, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.2472649035648797e-05, + "loss": 3.5609, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.2464263088138277e-05, + "loss": 3.557, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.2455877140627757e-05, + "loss": 3.5571, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.2447491193117236e-05, + "loss": 3.5573, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.2439121624410446e-05, + "loss": 3.5474, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.2430735676899926e-05, + "loss": 3.553, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.2422349729389405e-05, + "loss": 3.5608, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.2413963781878885e-05, + "loss": 3.5693, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.2405610591975824e-05, + "loss": 3.5664, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239722464446531e-05, + "loss": 3.533, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238883869695479e-05, + "loss": 3.5528, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238045274944427e-05, + "loss": 3.543, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237206680193375e-05, + "loss": 3.5596, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236368085442323e-05, + "loss": 3.5489, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235529490691271e-05, + "loss": 3.5545, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234690895940219e-05, + "loss": 3.5513, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.23385393906954e-05, + "loss": 3.5717, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.233015344318488e-05, + "loss": 3.5529, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232176749567436e-05, + "loss": 3.5578, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231338154816384e-05, + "loss": 3.5499, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230501197945705e-05, + "loss": 3.5645, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229662603194653e-05, + "loss": 3.5531, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228824008443601e-05, + "loss": 3.5489, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227985413692549e-05, + "loss": 3.5518, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2271484568218704e-05, + "loss": 3.5527, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.2263098620708184e-05, + "loss": 3.5474, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.2254712673197664e-05, + "loss": 3.5516, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.2246326725687144e-05, + "loss": 3.5515, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223795715698035e-05, + "loss": 3.5588, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222957120946983e-05, + "loss": 3.5587, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222118526195931e-05, + "loss": 3.5578, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221279931444879e-05, + "loss": 3.5554, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.2204429745742e-05, + "loss": 3.5613, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219604379823148e-05, + "loss": 3.5406, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218765785072096e-05, + "loss": 3.5493, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217927190321044e-05, + "loss": 3.5499, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.217090233450366e-05, + "loss": 3.5397, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216251638699314e-05, + "loss": 3.5509, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215413043948262e-05, + "loss": 3.5553, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.21457444919721e-05, + "loss": 3.5506, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.2137374923265307e-05, + "loss": 3.5577, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.2128988975754787e-05, + "loss": 3.5557, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2120603028244266e-05, + "loss": 3.5551, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2112217080733746e-05, + "loss": 3.5522, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2103847512026956e-05, + "loss": 3.5382, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2095461564516435e-05, + "loss": 3.5552, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.2087075617005915e-05, + "loss": 3.5517, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.2078689669495395e-05, + "loss": 3.5556, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207032010078861e-05, + "loss": 3.5469, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206193415327809e-05, + "loss": 3.5457, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205354820576757e-05, + "loss": 3.5378, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204516225825705e-05, + "loss": 3.5422, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203679268955026e-05, + "loss": 3.5512, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202840674203974e-05, + "loss": 3.5362, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.202002079452922e-05, + "loss": 3.5611, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.20116348470187e-05, + "loss": 3.5541, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200326527831191e-05, + "loss": 3.5304, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199487933080139e-05, + "loss": 3.5608, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198649338329087e-05, + "loss": 3.5382, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197810743578035e-05, + "loss": 3.5418, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.1969737867073565e-05, + "loss": 3.5402, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.1961351919563045e-05, + "loss": 3.5471, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.1952965972052525e-05, + "loss": 3.5389, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.1944580024542005e-05, + "loss": 3.551, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.1936210455835214e-05, + "loss": 3.527, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1927824508324694e-05, + "loss": 3.5401, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.1919438560814174e-05, + "loss": 3.5539, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.1911052613303654e-05, + "loss": 3.547, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190268304459686e-05, + "loss": 3.5558, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189429709708634e-05, + "loss": 3.5503, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188591114957582e-05, + "loss": 3.5605, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.18775252020653e-05, + "loss": 3.5419, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186915563335852e-05, + "loss": 3.5645, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.1860769685848e-05, + "loss": 3.5399, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185238373833748e-05, + "loss": 3.5423, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184399779082695e-05, + "loss": 3.5509, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183562822212017e-05, + "loss": 3.56, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182724227460965e-05, + "loss": 3.5505, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181885632709913e-05, + "loss": 3.5579, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.18104703795886e-05, + "loss": 3.5324, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180208443207808e-05, + "loss": 3.5295, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1793714863371296e-05, + "loss": 3.542, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.1785328915860776e-05, + "loss": 3.5497, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1776942968350256e-05, + "loss": 3.5413, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1768557020839736e-05, + "loss": 3.544, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.176018745213295e-05, + "loss": 3.5442, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.1751801504622425e-05, + "loss": 3.5424, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.1743415557111905e-05, + "loss": 3.5413, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.1735029609601385e-05, + "loss": 3.5401, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.17266600408946e-05, + "loss": 3.5534, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.1718274093384074e-05, + "loss": 3.5636, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.1709888145873554e-05, + "loss": 3.5542, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.1701502198363034e-05, + "loss": 3.5377, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169313262965625e-05, + "loss": 3.5468, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168474668214573e-05, + "loss": 3.5441, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167636073463521e-05, + "loss": 3.5531, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166797478712469e-05, + "loss": 3.5518, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.16596052184179e-05, + "loss": 3.5411, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165121927090738e-05, + "loss": 3.5432, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164283332339686e-05, + "loss": 3.5468, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163444737588634e-05, + "loss": 3.5504, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162607780717955e-05, + "loss": 3.5417, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161769185966903e-05, + "loss": 3.5432, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160930591215851e-05, + "loss": 3.5345, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160091996464799e-05, + "loss": 3.5459, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1592550395941204e-05, + "loss": 3.5352, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.1584164448430684e-05, + "loss": 3.5407, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.1575778500920164e-05, + "loss": 3.5393, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.1567392553409644e-05, + "loss": 3.5456, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155902298470285e-05, + "loss": 3.5408, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155063703719233e-05, + "loss": 3.5463, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154225108968181e-05, + "loss": 3.5551, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153386514217129e-05, + "loss": 3.5521, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.15254955734645e-05, + "loss": 3.5543, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151710962595398e-05, + "loss": 3.5464, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150872367844346e-05, + "loss": 3.5435, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150033773093294e-05, + "loss": 3.5451, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149196816222616e-05, + "loss": 3.5279, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148358221471564e-05, + "loss": 3.5476, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147519626720512e-05, + "loss": 3.5398, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.14668103196946e-05, + "loss": 3.5512, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1458440750987806e-05, + "loss": 3.5415, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1450054803477286e-05, + "loss": 3.5493, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.1441668855966766e-05, + "loss": 3.5389, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.1433282908456246e-05, + "loss": 3.544, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.1424913339749455e-05, + "loss": 3.5492, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.1416527392238935e-05, + "loss": 3.545, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.1408141444728415e-05, + "loss": 3.558, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.1399755497217895e-05, + "loss": 3.543, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139138592851111e-05, + "loss": 3.5508, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138299998100059e-05, + "loss": 3.5469, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137461403349007e-05, + "loss": 3.5447, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136622808597955e-05, + "loss": 3.5514, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135785851727276e-05, + "loss": 3.5399, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134947256976224e-05, + "loss": 3.5461, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134108662225172e-05, + "loss": 3.5513, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.13327006747412e-05, + "loss": 3.5398, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132433110603441e-05, + "loss": 3.5402, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131594515852389e-05, + "loss": 3.5486, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130755921101337e-05, + "loss": 3.5464, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129917326350285e-05, + "loss": 3.5421, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290803694796065e-05, + "loss": 3.548, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1282417747285545e-05, + "loss": 3.5413, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1274031799775025e-05, + "loss": 3.5595, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1265645852264505e-05, + "loss": 3.5414, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8414697647094727, + "eval_runtime": 305.5805, + "eval_samples_per_second": 1248.741, + "eval_steps_per_second": 39.024, + "step": 1144790 + }, + { + "epoch": 1.0, + "learning_rate": 3.1257276283557714e-05, + "loss": 3.5363, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1248890336047194e-05, + "loss": 3.5409, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.1240504388536674e-05, + "loss": 3.5354, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1232118441026154e-05, + "loss": 3.556, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122374887231936e-05, + "loss": 3.5443, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121536292480884e-05, + "loss": 3.5456, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120697697729832e-05, + "loss": 3.5398, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.11985910297878e-05, + "loss": 3.5417, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.119022146108101e-05, + "loss": 3.5332, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.11818355135705e-05, + "loss": 3.5398, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117344956605998e-05, + "loss": 3.5421, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116506361854946e-05, + "loss": 3.5533, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.1156710428646397e-05, + "loss": 3.5495, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.1148324481135877e-05, + "loss": 3.5208, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.1139938533625357e-05, + "loss": 3.5342, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.1131552586114836e-05, + "loss": 3.5301, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.1123166638604316e-05, + "loss": 3.5402, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1114780691093796e-05, + "loss": 3.5333, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1106394743583276e-05, + "loss": 3.5406, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.1098008796072756e-05, + "loss": 3.5343, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.1089639227365965e-05, + "loss": 3.5555, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108125327985545e-05, + "loss": 3.5412, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107286733234493e-05, + "loss": 3.5385, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106448138483441e-05, + "loss": 3.5341, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105611181612762e-05, + "loss": 3.5511, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.10477258686171e-05, + "loss": 3.5354, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103933992110658e-05, + "loss": 3.5316, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103095397359606e-05, + "loss": 3.5392, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102258440488927e-05, + "loss": 3.5335, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101419845737875e-05, + "loss": 3.5314, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100581250986823e-05, + "loss": 3.537, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099742656235771e-05, + "loss": 3.5355, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098905699365092e-05, + "loss": 3.5421, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0980671046140406e-05, + "loss": 3.5439, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0972285098629886e-05, + "loss": 3.541, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0963899151119366e-05, + "loss": 3.5375, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.0955529582412575e-05, + "loss": 3.5457, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0947143634902055e-05, + "loss": 3.5271, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.0938757687391535e-05, + "loss": 3.5345, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0930371739881015e-05, + "loss": 3.5337, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0922002171174224e-05, + "loss": 3.5272, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.0913616223663704e-05, + "loss": 3.535, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.0905230276153184e-05, + "loss": 3.54, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.0896844328642664e-05, + "loss": 3.5341, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088847475993587e-05, + "loss": 3.5409, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.088008881242536e-05, + "loss": 3.5414, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087170286491484e-05, + "loss": 3.5392, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086331691740432e-05, + "loss": 3.5391, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085494734869753e-05, + "loss": 3.5219, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084656140118701e-05, + "loss": 3.5379, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083817545367649e-05, + "loss": 3.5428, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082978950616597e-05, + "loss": 3.5379, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082141993745918e-05, + "loss": 3.5342, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081303398994866e-05, + "loss": 3.5303, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080464804243814e-05, + "loss": 3.5198, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079626209492762e-05, + "loss": 3.525, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.07878761474171e-05, + "loss": 3.5373, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077950657871031e-05, + "loss": 3.5254, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077112063119979e-05, + "loss": 3.543, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076273468368927e-05, + "loss": 3.5359, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.0754348736178746e-05, + "loss": 3.5226, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074597916747196e-05, + "loss": 3.5441, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073759321996144e-05, + "loss": 3.5229, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072920727245092e-05, + "loss": 3.5273, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.0720821324940395e-05, + "loss": 3.5245, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071245175623361e-05, + "loss": 3.5364, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070406580872309e-05, + "loss": 3.5218, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069567986121257e-05, + "loss": 3.5354, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068729391370205e-05, + "loss": 3.5111, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067892434499527e-05, + "loss": 3.5255, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067053839748475e-05, + "loss": 3.5382, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066215244997422e-05, + "loss": 3.5333, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.06537665024637e-05, + "loss": 3.5344, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0645396933756916e-05, + "loss": 3.5394, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.0637010986246396e-05, + "loss": 3.5446, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062862503873587e-05, + "loss": 3.5281, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.062023909122535e-05, + "loss": 3.5477, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0611869522518565e-05, + "loss": 3.526, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.0603483575008045e-05, + "loss": 3.5251, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059509762749752e-05, + "loss": 3.5341, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0586711679987005e-05, + "loss": 3.5405, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057834211128022e-05, + "loss": 3.5352, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.0569956163769694e-05, + "loss": 3.5423, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.0561570216259174e-05, + "loss": 3.522, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.0553184268748654e-05, + "loss": 3.5145, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054481470004187e-05, + "loss": 3.5259, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053642875253134e-05, + "loss": 3.5339, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052804280502082e-05, + "loss": 3.527, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051967323631404e-05, + "loss": 3.5253, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.051128728880352e-05, + "loss": 3.532, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502901341292995e-05, + "loss": 3.5243, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494515393782475e-05, + "loss": 3.5264, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.048614582507569e-05, + "loss": 3.526, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477759877565164e-05, + "loss": 3.5375, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469373930054644e-05, + "loss": 3.5491, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460987982544127e-05, + "loss": 3.5422, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452602035033607e-05, + "loss": 3.5179, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0444232466326816e-05, + "loss": 3.5332, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435846518816296e-05, + "loss": 3.53, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427460571305776e-05, + "loss": 3.5354, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0419091002598992e-05, + "loss": 3.5365, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.041070505508847e-05, + "loss": 3.5275, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.040231910757795e-05, + "loss": 3.5287, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.039393316006743e-05, + "loss": 3.5336, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0385563591360638e-05, + "loss": 3.5366, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0377177643850118e-05, + "loss": 3.5274, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368791696339598e-05, + "loss": 3.5266, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.036040574882908e-05, + "loss": 3.521, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035203618012229e-05, + "loss": 3.5307, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.034365023261177e-05, + "loss": 3.519, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.033526428510125e-05, + "loss": 3.5256, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.032687833759073e-05, + "loss": 3.5216, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318508768883942e-05, + "loss": 3.5348, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0310122821373422e-05, + "loss": 3.5266, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301736873862902e-05, + "loss": 3.5283, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293350926352382e-05, + "loss": 3.5434, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.028498135764559e-05, + "loss": 3.5366, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.027659541013507e-05, + "loss": 3.5399, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.026820946262455e-05, + "loss": 3.5301, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259823515114035e-05, + "loss": 3.5288, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251453946407244e-05, + "loss": 3.5273, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0243067998896724e-05, + "loss": 3.5174, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234682051386204e-05, + "loss": 3.5309, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0226296103875684e-05, + "loss": 3.5261, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217926535168896e-05, + "loss": 3.5346, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0209540587658376e-05, + "loss": 3.53, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0201154640147856e-05, + "loss": 3.5348, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192768692637336e-05, + "loss": 3.5278, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0184399123930545e-05, + "loss": 3.5259, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0176013176420025e-05, + "loss": 3.5328, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167627228909505e-05, + "loss": 3.5294, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0159241281398988e-05, + "loss": 3.5409, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150871712692197e-05, + "loss": 3.5302, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142485765181677e-05, + "loss": 3.5374, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0134099817671157e-05, + "loss": 3.5334, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125713870160637e-05, + "loss": 3.5292, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.011734430145385e-05, + "loss": 3.5304, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.010895835394333e-05, + "loss": 3.5288, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.010057240643281e-05, + "loss": 3.5316, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.009218645892229e-05, + "loss": 3.538, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.00838168902155e-05, + "loss": 3.5274, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.007543094270498e-05, + "loss": 3.5274, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.006704499519446e-05, + "loss": 3.5323, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058659047683942e-05, + "loss": 3.5313, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.005028947897715e-05, + "loss": 3.5285, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.004190353146663e-05, + "loss": 3.5367, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.003351758395611e-05, + "loss": 3.5256, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.002513163644559e-05, + "loss": 3.5417, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016762067738803e-05, + "loss": 3.527, + "step": 1220608 + }, + { + "epoch": 1.03, + "eval_loss": 3.842308282852173, + "eval_runtime": 305.5945, + "eval_samples_per_second": 1248.684, + "eval_steps_per_second": 39.022, + "step": 1221110 + }, + { + "epoch": 0.0, + "learning_rate": 3.0008376120228283e-05, + "loss": 3.4832, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999990172717763e-05, + "loss": 3.523, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991604225207243e-05, + "loss": 3.522, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9983218277696723e-05, + "loss": 3.5381, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974848708989932e-05, + "loss": 3.5326, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966462761479412e-05, + "loss": 3.5309, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9958076813968892e-05, + "loss": 3.526, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949690866458376e-05, + "loss": 3.5274, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9941321297751585e-05, + "loss": 3.5146, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932935350241065e-05, + "loss": 3.5286, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924549402730545e-05, + "loss": 3.5259, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9916163455220025e-05, + "loss": 3.5409, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9907810265316966e-05, + "loss": 3.5378, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9899424317806446e-05, + "loss": 3.5052, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9891038370295926e-05, + "loss": 3.5182, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882652422785406e-05, + "loss": 3.5188, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9874266475274886e-05, + "loss": 3.5205, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865880527764366e-05, + "loss": 3.5229, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9857494580253846e-05, + "loss": 3.5268, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.984910863274333e-05, + "loss": 3.5218, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840739064036538e-05, + "loss": 3.5403, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832353116526018e-05, + "loss": 3.5279, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823967169015498e-05, + "loss": 3.5211, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815581221504978e-05, + "loss": 3.5209, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.980721165279819e-05, + "loss": 3.5397, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.979882570528767e-05, + "loss": 3.5213, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.979043975777715e-05, + "loss": 3.5189, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.978205381026663e-05, + "loss": 3.5254, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.977368424155984e-05, + "loss": 3.5172, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976529829404932e-05, + "loss": 3.5207, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.97569123465388e-05, + "loss": 3.5206, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748526399028283e-05, + "loss": 3.5218, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9740156830321492e-05, + "loss": 3.5248, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731770882810972e-05, + "loss": 3.5274, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723384935300452e-05, + "loss": 3.5297, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714998987789932e-05, + "loss": 3.5255, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706629419083144e-05, + "loss": 3.5322, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9698243471572624e-05, + "loss": 3.5116, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689857524062104e-05, + "loss": 3.5227, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681471576551584e-05, + "loss": 3.5151, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9673102007844793e-05, + "loss": 3.5175, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664716060334273e-05, + "loss": 3.5182, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9656330112823753e-05, + "loss": 3.5277, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647944165313237e-05, + "loss": 3.5194, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639574596606446e-05, + "loss": 3.5271, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9631188649095926e-05, + "loss": 3.527, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622802701585406e-05, + "loss": 3.5282, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9614416754074886e-05, + "loss": 3.5186, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9606047185368098e-05, + "loss": 3.5078, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597661237857578e-05, + "loss": 3.5207, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9589275290347058e-05, + "loss": 3.5308, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580889342836538e-05, + "loss": 3.5221, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572519774129747e-05, + "loss": 3.5158, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9564133826619227e-05, + "loss": 3.5158, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555747879108707e-05, + "loss": 3.511, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.954736193159819e-05, + "loss": 3.5061, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538975984087663e-05, + "loss": 3.5279, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.953060641538088e-05, + "loss": 3.5109, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.952222046787036e-05, + "loss": 3.5246, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.951383452035984e-05, + "loss": 3.522, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.950546495165305e-05, + "loss": 3.5059, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.949707900414253e-05, + "loss": 3.5306, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.948869305663201e-05, + "loss": 3.5095, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9480307109121485e-05, + "loss": 3.5151, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.94719375404147e-05, + "loss": 3.5066, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.946355159290418e-05, + "loss": 3.5228, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.945516564539366e-05, + "loss": 3.5106, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446779697883137e-05, + "loss": 3.516, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9438410129176353e-05, + "loss": 3.5028, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9430024181665833e-05, + "loss": 3.5114, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421638234155313e-05, + "loss": 3.5202, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.941325228664479e-05, + "loss": 3.5273, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404882717938005e-05, + "loss": 3.5179, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396496770427485e-05, + "loss": 3.5206, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.938811082291696e-05, + "loss": 3.5314, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937972487540644e-05, + "loss": 3.5149, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9371355306699654e-05, + "loss": 3.5335, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9362969359189134e-05, + "loss": 3.5108, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935458341167861e-05, + "loss": 3.5132, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934619746416809e-05, + "loss": 3.5178, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337827895461307e-05, + "loss": 3.5269, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329441947950787e-05, + "loss": 3.5214, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.932105600044026e-05, + "loss": 3.5289, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312670052929743e-05, + "loss": 3.5106, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930430048422296e-05, + "loss": 3.4989, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295914536712432e-05, + "loss": 3.5113, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287528589201912e-05, + "loss": 3.5171, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9279142641691392e-05, + "loss": 3.512, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270773072984608e-05, + "loss": 3.5118, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262387125474085e-05, + "loss": 3.5199, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9254001177963564e-05, + "loss": 3.5139, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245615230453044e-05, + "loss": 3.5138, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.923724566174626e-05, + "loss": 3.512, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228859714235733e-05, + "loss": 3.5227, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220473766725213e-05, + "loss": 3.5336, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9212087819214697e-05, + "loss": 3.5251, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203718250507906e-05, + "loss": 3.5058, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9195332302997386e-05, + "loss": 3.5167, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186946355486866e-05, + "loss": 3.5179, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178560407976346e-05, + "loss": 3.5222, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9170190839269558e-05, + "loss": 3.5232, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161804891759038e-05, + "loss": 3.5145, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9153418944248518e-05, + "loss": 3.5107, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9145032996737998e-05, + "loss": 3.5211, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136647049227478e-05, + "loss": 3.5225, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9128277480520687e-05, + "loss": 3.5091, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119891533010167e-05, + "loss": 3.5168, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.911150558549965e-05, + "loss": 3.5103, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.910311963798913e-05, + "loss": 3.5126, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.909475006928234e-05, + "loss": 3.5082, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.908636412177182e-05, + "loss": 3.5122, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.90779781742613e-05, + "loss": 3.503, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.906959222675078e-05, + "loss": 3.521, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9061222658043992e-05, + "loss": 3.5117, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052836710533472e-05, + "loss": 3.5125, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044450763022952e-05, + "loss": 3.5292, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9036064815512432e-05, + "loss": 3.527, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.902769524680564e-05, + "loss": 3.5222, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901930929929512e-05, + "loss": 3.5208, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.90109233517846e-05, + "loss": 3.5128, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002537404274084e-05, + "loss": 3.5105, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8994167835567293e-05, + "loss": 3.5062, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985781888056773e-05, + "loss": 3.5116, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977395940546253e-05, + "loss": 3.5135, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8969009993035733e-05, + "loss": 3.52, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960640424328946e-05, + "loss": 3.5145, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8952254476818425e-05, + "loss": 3.5207, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943868529307905e-05, + "loss": 3.5162, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935482581797385e-05, + "loss": 3.5133, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8927113013090594e-05, + "loss": 3.5092, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918727065580074e-05, + "loss": 3.5246, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8910341118069554e-05, + "loss": 3.5232, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901955170559038e-05, + "loss": 3.519, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893585601852247e-05, + "loss": 3.5172, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8885199654341727e-05, + "loss": 3.5213, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876813706831207e-05, + "loss": 3.5174, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8868427759320687e-05, + "loss": 3.5188, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.88600581906139e-05, + "loss": 3.5131, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.885167224310338e-05, + "loss": 3.5182, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884328629559286e-05, + "loss": 3.5218, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.883490034808234e-05, + "loss": 3.5123, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826530779375548e-05, + "loss": 3.5134, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8818144831865028e-05, + "loss": 3.5183, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809758884354508e-05, + "loss": 3.5214, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.880137293684399e-05, + "loss": 3.5088, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.87930033681372e-05, + "loss": 3.5241, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.878461742062668e-05, + "loss": 3.5156, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.877623147311616e-05, + "loss": 3.5245, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.876784552560564e-05, + "loss": 3.5158, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759475956898853e-05, + "loss": 3.5077, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.843430280685425, + "eval_runtime": 306.3188, + "eval_samples_per_second": 1245.731, + "eval_steps_per_second": 38.93, + "step": 1297430 + }, + { + "epoch": 1.0, + "learning_rate": 2.8751090009388333e-05, + "loss": 3.51, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742704061877813e-05, + "loss": 3.5062, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8734318114367293e-05, + "loss": 3.5235, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725948545660502e-05, + "loss": 3.5147, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8717562598149982e-05, + "loss": 3.5186, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8709176650639462e-05, + "loss": 3.5144, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700790703128945e-05, + "loss": 3.5075, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8692421134422154e-05, + "loss": 3.5032, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8684035186911634e-05, + "loss": 3.5166, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8675649239401114e-05, + "loss": 3.5081, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8667263291890594e-05, + "loss": 3.5309, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8658893723183807e-05, + "loss": 3.5154, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8650524154477016e-05, + "loss": 3.5022, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8642138206966496e-05, + "loss": 3.4995, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8633752259455976e-05, + "loss": 3.5081, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8625366311945455e-05, + "loss": 3.5015, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8616980364434935e-05, + "loss": 3.5125, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8608594416924415e-05, + "loss": 3.5123, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.86002084694139e-05, + "loss": 3.5031, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591838900707108e-05, + "loss": 3.5288, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8583452953196588e-05, + "loss": 3.5096, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8575067005686068e-05, + "loss": 3.5103, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566681058175548e-05, + "loss": 3.5069, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.855831148946876e-05, + "loss": 3.526, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.854992554195824e-05, + "loss": 3.5058, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.854153959444772e-05, + "loss": 3.5097, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.85331536469372e-05, + "loss": 3.5069, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.852478407823041e-05, + "loss": 3.5075, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.851639813071989e-05, + "loss": 3.5046, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.850801218320937e-05, + "loss": 3.508, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8499626235698852e-05, + "loss": 3.5111, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.849125666699206e-05, + "loss": 3.51, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.848287071948154e-05, + "loss": 3.5148, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.847448477197102e-05, + "loss": 3.5173, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.84660988244605e-05, + "loss": 3.5099, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457729255753714e-05, + "loss": 3.5155, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8449343308243194e-05, + "loss": 3.5004, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8440957360732674e-05, + "loss": 3.5118, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8432571413222154e-05, + "loss": 3.499, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8424201844515363e-05, + "loss": 3.5066, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8415815897004843e-05, + "loss": 3.5017, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8407429949494323e-05, + "loss": 3.5134, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8399044001983806e-05, + "loss": 3.507, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390674433277015e-05, + "loss": 3.5159, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8382288485766495e-05, + "loss": 3.511, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8373902538255975e-05, + "loss": 3.5134, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8365516590745455e-05, + "loss": 3.5078, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8357147022038668e-05, + "loss": 3.4958, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348761074528147e-05, + "loss": 3.5035, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8340375127017627e-05, + "loss": 3.5191, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331989179507107e-05, + "loss": 3.5076, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323619610800316e-05, + "loss": 3.5027, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8315233663289796e-05, + "loss": 3.4998, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306847715779276e-05, + "loss": 3.5031, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8298461768268753e-05, + "loss": 3.4874, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.829009219956197e-05, + "loss": 3.5195, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.828170625205145e-05, + "loss": 3.4931, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.827332030454093e-05, + "loss": 3.5106, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264934357030405e-05, + "loss": 3.5084, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.825656478832362e-05, + "loss": 3.4974, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.82481788408131e-05, + "loss": 3.5123, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.823979289330258e-05, + "loss": 3.4986, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8231406945792054e-05, + "loss": 3.5015, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.822303737708527e-05, + "loss": 3.4898, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.821465142957475e-05, + "loss": 3.5103, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8206265482064227e-05, + "loss": 3.4974, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8197879534553707e-05, + "loss": 3.5031, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8189509965846923e-05, + "loss": 3.4869, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8181124018336402e-05, + "loss": 3.4972, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172738070825876e-05, + "loss": 3.5065, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.816435212331536e-05, + "loss": 3.5117, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.815598255460857e-05, + "loss": 3.5096, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147596607098055e-05, + "loss": 3.5089, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8139210659587528e-05, + "loss": 3.5141, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130824712077008e-05, + "loss": 3.5036, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122455143370224e-05, + "loss": 3.516, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.81140691958597e-05, + "loss": 3.5014, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.810568324834918e-05, + "loss": 3.5009, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.809729730083866e-05, + "loss": 3.4999, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8088927732131876e-05, + "loss": 3.5122, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.808054178462135e-05, + "loss": 3.5097, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.807215583711083e-05, + "loss": 3.5135, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.806376988960031e-05, + "loss": 3.5031, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8055400320893525e-05, + "loss": 3.4854, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8047014373383002e-05, + "loss": 3.4955, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803862842587248e-05, + "loss": 3.5021, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.803024247836196e-05, + "loss": 3.5024, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8021872909655174e-05, + "loss": 3.4976, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8013486962144654e-05, + "loss": 3.5087, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8005101014634134e-05, + "loss": 3.4975, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996715067123614e-05, + "loss": 3.4968, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7988345498416823e-05, + "loss": 3.5029, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979959550906303e-05, + "loss": 3.5079, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.7971573603395783e-05, + "loss": 3.5163, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7963187655885263e-05, + "loss": 3.519, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954818087178475e-05, + "loss": 3.4881, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7946432139667955e-05, + "loss": 3.5064, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7938046192157435e-05, + "loss": 3.5042, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929660244646915e-05, + "loss": 3.5062, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7921290675940124e-05, + "loss": 3.5151, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912904728429608e-05, + "loss": 3.4981, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7904518780919088e-05, + "loss": 3.4978, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7896132833408568e-05, + "loss": 3.5089, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887763264701777e-05, + "loss": 3.511, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7879377317191257e-05, + "loss": 3.4924, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870991369680737e-05, + "loss": 3.5052, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862605422170217e-05, + "loss": 3.4964, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.785423585346343e-05, + "loss": 3.497, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.784584990595291e-05, + "loss": 3.4957, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.783746395844239e-05, + "loss": 3.4984, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.782907801093187e-05, + "loss": 3.4916, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820708442225078e-05, + "loss": 3.5073, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.781232249471456e-05, + "loss": 3.4988, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.780393654720404e-05, + "loss": 3.5005, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.779555059969352e-05, + "loss": 3.5144, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.778718103098673e-05, + "loss": 3.5124, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.777879508347621e-05, + "loss": 3.5058, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.777040913596569e-05, + "loss": 3.5076, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.776202318845517e-05, + "loss": 3.4992, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753653619748383e-05, + "loss": 3.4977, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7745267672237863e-05, + "loss": 3.4921, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736881724727343e-05, + "loss": 3.4986, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728495777216823e-05, + "loss": 3.5022, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7720126208510032e-05, + "loss": 3.505, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7711740260999515e-05, + "loss": 3.5028, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7703354313488995e-05, + "loss": 3.5058, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694968365978475e-05, + "loss": 3.5028, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7686598797271684e-05, + "loss": 3.4987, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7678212849761164e-05, + "loss": 3.4964, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7669826902250644e-05, + "loss": 3.5125, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7661440954740124e-05, + "loss": 3.5106, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7653071386033336e-05, + "loss": 3.5065, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7644685438522816e-05, + "loss": 3.503, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7636299491012296e-05, + "loss": 3.5046, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627913543501776e-05, + "loss": 3.5053, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7619543974794985e-05, + "loss": 3.5096, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.761115802728447e-05, + "loss": 3.5023, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.760277207977395e-05, + "loss": 3.5049, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.759438613226343e-05, + "loss": 3.5029, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7586016563556638e-05, + "loss": 3.5021, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577630616046118e-05, + "loss": 3.5016, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7569244668535598e-05, + "loss": 3.5049, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560858721025078e-05, + "loss": 3.5068, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.755248915231829e-05, + "loss": 3.4959, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.754410320480777e-05, + "loss": 3.5121, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.753571725729725e-05, + "loss": 3.5013, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.752733130978673e-05, + "loss": 3.5088, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.751896174107994e-05, + "loss": 3.5036, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510575793569422e-05, + "loss": 3.4936, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.845076084136963, + "eval_runtime": 305.6641, + "eval_samples_per_second": 1248.4, + "eval_steps_per_second": 39.013, + "step": 1373750 + }, + { + "epoch": 0.0, + "learning_rate": 2.7502189846058902e-05, + "loss": 3.4964, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493803898548382e-05, + "loss": 3.4933, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485417951037862e-05, + "loss": 3.5108, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7477032003527342e-05, + "loss": 3.4989, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.746866243482055e-05, + "loss": 3.5107, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.746027648731003e-05, + "loss": 3.4991, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451890539799515e-05, + "loss": 3.4998, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443520971092724e-05, + "loss": 3.4878, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7435135023582204e-05, + "loss": 3.501, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426749076071684e-05, + "loss": 3.4985, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7418363128561164e-05, + "loss": 3.5138, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409977181050644e-05, + "loss": 3.5017, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401623991147585e-05, + "loss": 3.489, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7393238043637065e-05, + "loss": 3.4884, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384852096126545e-05, + "loss": 3.5011, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7376466148616025e-05, + "loss": 3.482, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7368080201105505e-05, + "loss": 3.4999, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359694253594985e-05, + "loss": 3.5004, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7351308306084468e-05, + "loss": 3.4928, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342938737377677e-05, + "loss": 3.5185, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7334552789867157e-05, + "loss": 3.4963, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7326166842356637e-05, + "loss": 3.4989, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317780894846117e-05, + "loss": 3.4943, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.730941132613933e-05, + "loss": 3.5119, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.730102537862881e-05, + "loss": 3.4845, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.729263943111829e-05, + "loss": 3.5003, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.728425348360777e-05, + "loss": 3.4894, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.727588391490098e-05, + "loss": 3.4953, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.726749796739046e-05, + "loss": 3.496, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725911201987994e-05, + "loss": 3.4926, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.725072607236942e-05, + "loss": 3.4978, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.724235650366263e-05, + "loss": 3.4986, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.723397055615211e-05, + "loss": 3.497, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.722558460864159e-05, + "loss": 3.509, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.721719866113107e-05, + "loss": 3.4927, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.720882909242428e-05, + "loss": 3.5021, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7200443144913763e-05, + "loss": 3.4903, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7192057197403243e-05, + "loss": 3.4945, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183671249892723e-05, + "loss": 3.4864, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7175301681185932e-05, + "loss": 3.4926, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166915733675412e-05, + "loss": 3.4898, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158529786164892e-05, + "loss": 3.5022, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7150143838654372e-05, + "loss": 3.4904, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141774269947585e-05, + "loss": 3.5006, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7133388322437065e-05, + "loss": 3.5027, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7125002374926545e-05, + "loss": 3.4972, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116616427416018e-05, + "loss": 3.497, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7108246858709234e-05, + "loss": 3.4835, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099860911198717e-05, + "loss": 3.4932, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7091474963688197e-05, + "loss": 3.5017, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.708308901617767e-05, + "loss": 3.4938, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074719447470886e-05, + "loss": 3.4945, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7066333499960366e-05, + "loss": 3.4825, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057947552449846e-05, + "loss": 3.4906, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049561604939322e-05, + "loss": 3.4742, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.704119203623254e-05, + "loss": 3.5068, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.703280608872202e-05, + "loss": 3.4797, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.702442014121149e-05, + "loss": 3.5031, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.701603419370097e-05, + "loss": 3.4939, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007664624994187e-05, + "loss": 3.4791, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.699927867748367e-05, + "loss": 3.5027, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990892729973144e-05, + "loss": 3.4878, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982506782462624e-05, + "loss": 3.4866, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.697413721375584e-05, + "loss": 3.4788, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.696575126624532e-05, + "loss": 3.4991, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6957365318734796e-05, + "loss": 3.4847, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6948979371224276e-05, + "loss": 3.4874, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940609802517492e-05, + "loss": 3.4757, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6932223855006965e-05, + "loss": 3.487, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923837907496445e-05, + "loss": 3.4908, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6915451959985925e-05, + "loss": 3.4977, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.690708239127914e-05, + "loss": 3.4928, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898696443768618e-05, + "loss": 3.5003, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6890310496258098e-05, + "loss": 3.4974, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881924548747577e-05, + "loss": 3.4903, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873554980040793e-05, + "loss": 3.4998, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.686516903253027e-05, + "loss": 3.493, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.685678308501975e-05, + "loss": 3.4866, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.684839713750923e-05, + "loss": 3.4884, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.684002756880244e-05, + "loss": 3.4985, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.683164162129192e-05, + "loss": 3.4997, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.68232556737814e-05, + "loss": 3.501, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.681486972627088e-05, + "loss": 3.4902, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.680650015756409e-05, + "loss": 3.4689, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.679811421005357e-05, + "loss": 3.4847, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.678972826254305e-05, + "loss": 3.4912, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.678134231503253e-05, + "loss": 3.4877, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.677297274632574e-05, + "loss": 3.4842, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764586798815224e-05, + "loss": 3.4964, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6756200851304704e-05, + "loss": 3.4878, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747814903794184e-05, + "loss": 3.4779, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739445335087393e-05, + "loss": 3.4906, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6731059387576873e-05, + "loss": 3.4996, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722673440066353e-05, + "loss": 3.4981, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6714287492555832e-05, + "loss": 3.5034, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705917923849045e-05, + "loss": 3.4815, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697531976338525e-05, + "loss": 3.4929, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6689146028828005e-05, + "loss": 3.4914, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680760081317485e-05, + "loss": 3.492, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6672390512610694e-05, + "loss": 3.4986, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6664004565100177e-05, + "loss": 3.4861, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6655618617589657e-05, + "loss": 3.4858, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6647232670079137e-05, + "loss": 3.4944, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638863101372346e-05, + "loss": 3.4988, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6630477153861826e-05, + "loss": 3.4807, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6622091206351306e-05, + "loss": 3.4871, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613705258840786e-05, + "loss": 3.4909, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6605335690134e-05, + "loss": 3.4858, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.659694974262348e-05, + "loss": 3.4791, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.658856379511296e-05, + "loss": 3.4838, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.658017784760244e-05, + "loss": 3.4822, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571808278895648e-05, + "loss": 3.4919, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.656342233138513e-05, + "loss": 3.4839, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.655503638387461e-05, + "loss": 3.4894, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.654665043636409e-05, + "loss": 3.5015, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.65382808676573e-05, + "loss": 3.5012, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.652989492014678e-05, + "loss": 3.4912, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.652150897263626e-05, + "loss": 3.4975, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.651312302512574e-05, + "loss": 3.4862, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504753456418952e-05, + "loss": 3.4836, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6496367508908432e-05, + "loss": 3.483, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487981561397912e-05, + "loss": 3.4818, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479595613887392e-05, + "loss": 3.4863, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.64712260451806e-05, + "loss": 3.4959, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462840097670085e-05, + "loss": 3.4892, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454454150159565e-05, + "loss": 3.4918, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6446068202649045e-05, + "loss": 3.4906, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437698633942254e-05, + "loss": 3.4851, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6429312686431734e-05, + "loss": 3.4843, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6420926738921214e-05, + "loss": 3.4989, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6412540791410693e-05, + "loss": 3.4985, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6404171222703906e-05, + "loss": 3.494, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6395785275193386e-05, + "loss": 3.4893, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6387399327682866e-05, + "loss": 3.4898, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6379013380172346e-05, + "loss": 3.4894, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370643811465555e-05, + "loss": 3.5047, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6362257863955038e-05, + "loss": 3.4887, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353871916444518e-05, + "loss": 3.4892, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6345485968933998e-05, + "loss": 3.4882, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6337116400227207e-05, + "loss": 3.4916, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328730452716687e-05, + "loss": 3.4884, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320344505206167e-05, + "loss": 3.4922, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311958557695647e-05, + "loss": 3.4956, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.630358898898886e-05, + "loss": 3.4833, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.629520304147834e-05, + "loss": 3.4963, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.628681709396782e-05, + "loss": 3.4945, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.62784311464573e-05, + "loss": 3.4909, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.627006157775051e-05, + "loss": 3.4913, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.626167563023999e-05, + "loss": 3.4789, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.847452163696289, + "eval_runtime": 329.2015, + "eval_samples_per_second": 1159.141, + "eval_steps_per_second": 36.224, + "step": 1450070 + }, + { + "epoch": 1.0, + "learning_rate": 2.6253289682729472e-05, + "loss": 3.4862, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244903735218952e-05, + "loss": 3.4847, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.623653416651216e-05, + "loss": 3.4999, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.622814821900164e-05, + "loss": 3.4847, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.621976227149112e-05, + "loss": 3.5001, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.62113763239806e-05, + "loss": 3.4812, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6203006755273813e-05, + "loss": 3.4899, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6194620807763293e-05, + "loss": 3.4756, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6186234860252773e-05, + "loss": 3.4901, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6177848912742253e-05, + "loss": 3.4828, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6169479344035462e-05, + "loss": 3.5017, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6161093396524942e-05, + "loss": 3.4888, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152723827818155e-05, + "loss": 3.4766, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6144337880307635e-05, + "loss": 3.4757, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135951932797115e-05, + "loss": 3.4888, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127565985286595e-05, + "loss": 3.4732, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6119180037776075e-05, + "loss": 3.4839, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6110794090265554e-05, + "loss": 3.4848, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6102408142755034e-05, + "loss": 3.4806, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6094038574048247e-05, + "loss": 3.5037, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085652626537727e-05, + "loss": 3.4871, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6077266679027207e-05, + "loss": 3.4822, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6068880731516687e-05, + "loss": 3.4833, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6060511162809896e-05, + "loss": 3.4982, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.605212521529938e-05, + "loss": 3.4747, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.604373926778886e-05, + "loss": 3.4835, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.603535332027834e-05, + "loss": 3.4805, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026983751571548e-05, + "loss": 3.4833, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018597804061028e-05, + "loss": 3.4811, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6010211856550508e-05, + "loss": 3.4765, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.6001825909039988e-05, + "loss": 3.4891, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.59934563403332e-05, + "loss": 3.4863, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.598507039282268e-05, + "loss": 3.4881, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.597668444531216e-05, + "loss": 3.4939, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.596829849780164e-05, + "loss": 3.4821, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5959912550291117e-05, + "loss": 3.4896, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5951542981584333e-05, + "loss": 3.4751, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5943157034073813e-05, + "loss": 3.4861, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5934771086563293e-05, + "loss": 3.4722, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5926401517856502e-05, + "loss": 3.4806, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5918015570345982e-05, + "loss": 3.4784, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5909629622835462e-05, + "loss": 3.4899, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.590124367532494e-05, + "loss": 3.4767, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5892874106618154e-05, + "loss": 3.4841, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5884488159107634e-05, + "loss": 3.4944, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5876102211597114e-05, + "loss": 3.4853, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5867716264086587e-05, + "loss": 3.4879, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5859346695379803e-05, + "loss": 3.47, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5850960747869287e-05, + "loss": 3.4773, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842574800358767e-05, + "loss": 3.4891, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.583418885284824e-05, + "loss": 3.4816, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5825819284141456e-05, + "loss": 3.4796, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5817433336630936e-05, + "loss": 3.4737, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5809047389120412e-05, + "loss": 3.4781, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800661441609892e-05, + "loss": 3.4618, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5792291872903108e-05, + "loss": 3.4882, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783905925392588e-05, + "loss": 3.473, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.577551997788206e-05, + "loss": 3.4845, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.576713403037154e-05, + "loss": 3.4857, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5758764461664757e-05, + "loss": 3.468, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5750378514154233e-05, + "loss": 3.4862, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741992566643713e-05, + "loss": 3.4751, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5733606619133193e-05, + "loss": 3.4752, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.572523705042641e-05, + "loss": 3.4656, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5716851102915886e-05, + "loss": 3.4826, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.5708465155405366e-05, + "loss": 3.4736, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.5700079207894846e-05, + "loss": 3.4759, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.569170963918806e-05, + "loss": 3.4621, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5683323691677535e-05, + "loss": 3.4709, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5674937744167015e-05, + "loss": 3.4764, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666551796656495e-05, + "loss": 3.4884, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5658182227949707e-05, + "loss": 3.4757, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5649796280439187e-05, + "loss": 3.4889, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5641410332928667e-05, + "loss": 3.4879, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5633024385418147e-05, + "loss": 3.4793, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624654816711356e-05, + "loss": 3.4839, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.561626886920084e-05, + "loss": 3.4813, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.560788292169032e-05, + "loss": 3.4781, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.55994969741798e-05, + "loss": 3.4735, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.559112740547301e-05, + "loss": 3.4873, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.558274145796249e-05, + "loss": 3.4876, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.557435551045197e-05, + "loss": 3.4873, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.556596956294145e-05, + "loss": 3.4788, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.555759999423466e-05, + "loss": 3.4612, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.554921404672414e-05, + "loss": 3.471, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.554082809921362e-05, + "loss": 3.4744, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.55324421517031e-05, + "loss": 3.4801, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.552407258299631e-05, + "loss": 3.4711, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5515686635485793e-05, + "loss": 3.48, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5507300687975273e-05, + "loss": 3.4757, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5498914740464753e-05, + "loss": 3.4669, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5490545171757962e-05, + "loss": 3.4797, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5482159224247442e-05, + "loss": 3.4852, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473773276736922e-05, + "loss": 3.4843, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5465387329226402e-05, + "loss": 3.4933, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5457017760519614e-05, + "loss": 3.4731, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5448631813009094e-05, + "loss": 3.4776, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5440245865498574e-05, + "loss": 3.4805, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431859917988054e-05, + "loss": 3.4819, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5423490349281263e-05, + "loss": 3.4845, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5415104401770747e-05, + "loss": 3.4755, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406718454260227e-05, + "loss": 3.475, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5398332506749707e-05, + "loss": 3.4801, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5389962938042916e-05, + "loss": 3.4864, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5381576990532396e-05, + "loss": 3.4677, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5373191043021876e-05, + "loss": 3.4776, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5364805095511356e-05, + "loss": 3.475, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5356435526804568e-05, + "loss": 3.4723, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5348049579294048e-05, + "loss": 3.465, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5339663631783528e-05, + "loss": 3.4743, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5331277684273008e-05, + "loss": 3.4727, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5322908115566217e-05, + "loss": 3.4755, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5314522168055697e-05, + "loss": 3.4749, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.530613622054518e-05, + "loss": 3.4733, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.529775027303466e-05, + "loss": 3.4906, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.528938070432787e-05, + "loss": 3.4886, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.528099475681735e-05, + "loss": 3.4794, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.527260880930683e-05, + "loss": 3.4848, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.526422286179631e-05, + "loss": 3.4744, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.5255853293089522e-05, + "loss": 3.4752, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5247467345579002e-05, + "loss": 3.469, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5239081398068482e-05, + "loss": 3.468, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.523069545055796e-05, + "loss": 3.4758, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.522232588185117e-05, + "loss": 3.4821, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.521393993434065e-05, + "loss": 3.4762, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5205553986830134e-05, + "loss": 3.4824, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5197168039319614e-05, + "loss": 3.4755, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188798470612823e-05, + "loss": 3.4727, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5180412523102303e-05, + "loss": 3.4723, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5172026575591783e-05, + "loss": 3.4863, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163640628081263e-05, + "loss": 3.4916, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5155271059374475e-05, + "loss": 3.4807, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146885111863955e-05, + "loss": 3.4751, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138499164353435e-05, + "loss": 3.4791, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5130113216842915e-05, + "loss": 3.4745, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5121743648136124e-05, + "loss": 3.4905, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5113357700625604e-05, + "loss": 3.4748, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104971753115088e-05, + "loss": 3.4789, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096585805604568e-05, + "loss": 3.4727, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5088216236897777e-05, + "loss": 3.4828, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5079830289387257e-05, + "loss": 3.4748, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5071444341876737e-05, + "loss": 3.4777, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5063058394366217e-05, + "loss": 3.4825, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.505468882565943e-05, + "loss": 3.4723, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.504630287814891e-05, + "loss": 3.4824, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.503791693063839e-05, + "loss": 3.4868, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.502953098312787e-05, + "loss": 3.4788, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5021161414421078e-05, + "loss": 3.4787, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5012775466910558e-05, + "loss": 3.4682, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.849039316177368, + "eval_runtime": 308.6562, + "eval_samples_per_second": 1236.298, + "eval_steps_per_second": 38.635, + "step": 1526390 + }, + { + "epoch": 0.0, + "learning_rate": 2.500438951940004e-05, + "loss": 3.4683, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499600357188952e-05, + "loss": 3.4692, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4987617624378998e-05, + "loss": 3.4857, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4979231676868478e-05, + "loss": 3.4762, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.497086210816169e-05, + "loss": 3.4877, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.496247616065117e-05, + "loss": 3.468, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.495409021314065e-05, + "loss": 3.4797, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494570426563013e-05, + "loss": 3.4618, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4937334696923343e-05, + "loss": 3.4778, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492894874941282e-05, + "loss": 3.4703, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.49205628019023e-05, + "loss": 3.487, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.491217685439178e-05, + "loss": 3.4815, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903823664488724e-05, + "loss": 3.4607, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895437716978204e-05, + "loss": 3.4666, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4887051769467684e-05, + "loss": 3.4749, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878665821957164e-05, + "loss": 3.4631, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.487027987444664e-05, + "loss": 3.4704, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.486189392693612e-05, + "loss": 3.473, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853507979425604e-05, + "loss": 3.4717, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4845122031915084e-05, + "loss": 3.4908, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836752463208293e-05, + "loss": 3.4737, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4828366515697773e-05, + "loss": 3.4703, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819980568187253e-05, + "loss": 3.4744, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811594620676733e-05, + "loss": 3.4817, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4803225051969945e-05, + "loss": 3.4679, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794839104459425e-05, + "loss": 3.476, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786453156948905e-05, + "loss": 3.4664, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4778083588242114e-05, + "loss": 3.4687, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4769697640731594e-05, + "loss": 3.4675, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4761311693221074e-05, + "loss": 3.4688, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752925745710558e-05, + "loss": 3.4707, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744556177003767e-05, + "loss": 3.4778, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4736170229493247e-05, + "loss": 3.4782, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727784281982727e-05, + "loss": 3.4831, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719398334472207e-05, + "loss": 3.4631, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4711012386961687e-05, + "loss": 3.4783, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.47026428182549e-05, + "loss": 3.4665, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469425687074438e-05, + "loss": 3.4745, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.468587092323386e-05, + "loss": 3.4587, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.467748497572334e-05, + "loss": 3.4664, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4669115407016548e-05, + "loss": 3.4654, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660729459506028e-05, + "loss": 3.4813, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.465234351199551e-05, + "loss": 3.4691, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464397394328872e-05, + "loss": 3.4681, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.46355879957782e-05, + "loss": 3.4851, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.462720204826768e-05, + "loss": 3.472, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.461881610075716e-05, + "loss": 3.4762, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610446532050373e-05, + "loss": 3.4643, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4602060584539853e-05, + "loss": 3.4605, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593674637029333e-05, + "loss": 3.478, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4585288689518813e-05, + "loss": 3.4711, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576919120812022e-05, + "loss": 3.4622, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.45685331733015e-05, + "loss": 3.4662, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.456014722579098e-05, + "loss": 3.468, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551761278280465e-05, + "loss": 3.4504, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4543391709573674e-05, + "loss": 3.4752, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4535005762063154e-05, + "loss": 3.4618, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526619814552634e-05, + "loss": 3.467, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4518233867042114e-05, + "loss": 3.4752, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509864298335326e-05, + "loss": 3.4602, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501478350824806e-05, + "loss": 3.4691, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4493092403314286e-05, + "loss": 3.4642, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484706455803766e-05, + "loss": 3.4599, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4476336887096975e-05, + "loss": 3.4596, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467950939586455e-05, + "loss": 3.4661, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459564992075935e-05, + "loss": 3.4628, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.445117904456542e-05, + "loss": 3.462, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442809475858628e-05, + "loss": 3.4543, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434423528348108e-05, + "loss": 3.4578, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4426037580837588e-05, + "loss": 3.4642, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417651633327064e-05, + "loss": 3.4797, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440928206462028e-05, + "loss": 3.4636, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.440089611710976e-05, + "loss": 3.4755, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439251016959924e-05, + "loss": 3.4745, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4384124222088717e-05, + "loss": 3.4652, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.437575465338193e-05, + "loss": 3.4709, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.436736870587141e-05, + "loss": 3.4756, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435898275836089e-05, + "loss": 3.465, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.435059681085037e-05, + "loss": 3.463, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.434222724214358e-05, + "loss": 3.4761, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.433384129463306e-05, + "loss": 3.4724, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325455347122538e-05, + "loss": 3.4717, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4317069399612018e-05, + "loss": 3.4683, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308699830905234e-05, + "loss": 3.4532, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4300313883394714e-05, + "loss": 3.4533, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.429192793588419e-05, + "loss": 3.4649, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428354198837367e-05, + "loss": 3.4662, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4275172419666883e-05, + "loss": 3.4627, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266786472156363e-05, + "loss": 3.4678, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258400524645843e-05, + "loss": 3.4628, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4250014577135323e-05, + "loss": 3.4556, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241645008428535e-05, + "loss": 3.465, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.423325906091801e-05, + "loss": 3.4683, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422487311340749e-05, + "loss": 3.4775, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.421648716589697e-05, + "loss": 3.4726, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4208117597190187e-05, + "loss": 3.4689, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199731649679664e-05, + "loss": 3.4566, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4191345702169144e-05, + "loss": 3.472, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182959754658624e-05, + "loss": 3.4669, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174590185951836e-05, + "loss": 3.474, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4166204238441313e-05, + "loss": 3.4663, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157818290930796e-05, + "loss": 3.459, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4149432343420276e-05, + "loss": 3.4693, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4141062774713485e-05, + "loss": 3.4746, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132676827202965e-05, + "loss": 3.4597, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4124290879692445e-05, + "loss": 3.465, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115904932181925e-05, + "loss": 3.4645, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107535363475138e-05, + "loss": 3.4564, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4099149415964618e-05, + "loss": 3.4546, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090763468454098e-05, + "loss": 3.4656, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4082377520943578e-05, + "loss": 3.4588, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4074007952236787e-05, + "loss": 3.4626, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065622004726267e-05, + "loss": 3.4633, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.405723605721575e-05, + "loss": 3.4618, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404885010970523e-05, + "loss": 3.4786, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.404048054099844e-05, + "loss": 3.4795, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.403209459348792e-05, + "loss": 3.4684, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.40237086459774e-05, + "loss": 3.4727, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.401532269846688e-05, + "loss": 3.4587, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.400695312976009e-05, + "loss": 3.4633, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.399856718224957e-05, + "loss": 3.4584, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.399018123473905e-05, + "loss": 3.4607, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.398179528722853e-05, + "loss": 3.4635, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.397342571852174e-05, + "loss": 3.4686, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.396503977101122e-05, + "loss": 3.4649, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956653823500704e-05, + "loss": 3.4698, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3948267875990184e-05, + "loss": 3.4641, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939898307283393e-05, + "loss": 3.4586, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3931512359772873e-05, + "loss": 3.4604, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3923126412262353e-05, + "loss": 3.4752, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914740464751833e-05, + "loss": 3.4772, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3906370896045045e-05, + "loss": 3.4709, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897984948534525e-05, + "loss": 3.4635, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889599001024005e-05, + "loss": 3.4674, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3881213053513485e-05, + "loss": 3.4623, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872843484806694e-05, + "loss": 3.4758, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3864457537296174e-05, + "loss": 3.4625, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3856071589785657e-05, + "loss": 3.465, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847685642275137e-05, + "loss": 3.4623, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3839316073568346e-05, + "loss": 3.4739, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830930126057826e-05, + "loss": 3.4618, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822544178547306e-05, + "loss": 3.4642, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3814158231036786e-05, + "loss": 3.4699, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380578866233e-05, + "loss": 3.4629, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.379740271481948e-05, + "loss": 3.4691, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.378901676730896e-05, + "loss": 3.4769, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780630819798435e-05, + "loss": 3.4677, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3772261251091648e-05, + "loss": 3.4624, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763875303581128e-05, + "loss": 3.4615, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8520126342773438, + "eval_runtime": 310.2661, + "eval_samples_per_second": 1229.883, + "eval_steps_per_second": 38.435, + "step": 1602710 + }, + { + "epoch": 1.0, + "learning_rate": 2.375548935607061e-05, + "loss": 3.4631, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3747103408560088e-05, + "loss": 3.4566, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.37387338398533e-05, + "loss": 3.4727, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.373034789234278e-05, + "loss": 3.4651, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.372196194483226e-05, + "loss": 3.473, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713575997321736e-05, + "loss": 3.4615, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.3705206428614952e-05, + "loss": 3.4653, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.3696820481104432e-05, + "loss": 3.4502, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.368843453359391e-05, + "loss": 3.4655, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.368004858608339e-05, + "loss": 3.4588, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.36716790173766e-05, + "loss": 3.4698, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.366329306986608e-05, + "loss": 3.4702, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3654923501159294e-05, + "loss": 3.4486, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3646537553648774e-05, + "loss": 3.4542, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.3638151606138254e-05, + "loss": 3.4635, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3629765658627734e-05, + "loss": 3.452, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.362137971111721e-05, + "loss": 3.4591, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.361299376360669e-05, + "loss": 3.4613, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604607816096173e-05, + "loss": 3.4594, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3596221868585653e-05, + "loss": 3.4746, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3587852299878863e-05, + "loss": 3.4612, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.3579466352368343e-05, + "loss": 3.461, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.3571080404857822e-05, + "loss": 3.4649, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3562694457347302e-05, + "loss": 3.4643, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3554324888640515e-05, + "loss": 3.4584, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545938941129995e-05, + "loss": 3.465, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537552993619475e-05, + "loss": 3.4557, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3529167046108955e-05, + "loss": 3.455, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3520797477402164e-05, + "loss": 3.4572, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3512411529891644e-05, + "loss": 3.4593, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3504025582381127e-05, + "loss": 3.4572, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3495656013674336e-05, + "loss": 3.4647, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3487270066163816e-05, + "loss": 3.4648, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478884118653296e-05, + "loss": 3.4689, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3470498171142776e-05, + "loss": 3.4545, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.346212860243599e-05, + "loss": 3.4672, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345374265492547e-05, + "loss": 3.4565, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.344535670741495e-05, + "loss": 3.4583, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.343697075990443e-05, + "loss": 3.4478, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3428601191197638e-05, + "loss": 3.454, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3420215243687118e-05, + "loss": 3.4564, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3411829296176597e-05, + "loss": 3.4659, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.340344334866608e-05, + "loss": 3.4551, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.339507377995929e-05, + "loss": 3.4585, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.338668783244877e-05, + "loss": 3.4743, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.337830188493825e-05, + "loss": 3.4623, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.336991593742773e-05, + "loss": 3.4625, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3361546368720942e-05, + "loss": 3.4543, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3353160421210422e-05, + "loss": 3.4425, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.3344774473699902e-05, + "loss": 3.469, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.3336388526189382e-05, + "loss": 3.4586, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.332801895748259e-05, + "loss": 3.4542, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.331963300997207e-05, + "loss": 3.4575, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.331124706246155e-05, + "loss": 3.4583, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3302861114951034e-05, + "loss": 3.4345, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.3294491546244244e-05, + "loss": 3.4653, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3286105598733724e-05, + "loss": 3.4495, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.3277719651223204e-05, + "loss": 3.4559, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3269333703712683e-05, + "loss": 3.46, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3260964135005896e-05, + "loss": 3.4538, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252578187495376e-05, + "loss": 3.4549, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3244192239984856e-05, + "loss": 3.4572, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3235806292474336e-05, + "loss": 3.4439, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.3227436723767545e-05, + "loss": 3.4505, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.3219050776257025e-05, + "loss": 3.4546, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.3210664828746505e-05, + "loss": 3.4537, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3202278881235985e-05, + "loss": 3.4501, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193909312529197e-05, + "loss": 3.4451, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3185523365018677e-05, + "loss": 3.4478, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3177137417508157e-05, + "loss": 3.4494, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.3168751469997634e-05, + "loss": 3.4639, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.316038190129085e-05, + "loss": 3.4503, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.315199595378033e-05, + "loss": 3.4683, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3143610006269806e-05, + "loss": 3.4641, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3135224058759286e-05, + "loss": 3.4551, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.31268544900525e-05, + "loss": 3.4551, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.311846854254198e-05, + "loss": 3.4613, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.311008259503146e-05, + "loss": 3.4569, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.310169664752094e-05, + "loss": 3.4486, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.309332707881415e-05, + "loss": 3.465, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.308494113130363e-05, + "loss": 3.4592, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076555183793107e-05, + "loss": 3.4615, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3068169236282587e-05, + "loss": 3.4587, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.30597996675758e-05, + "loss": 3.4402, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.305141372006528e-05, + "loss": 3.444, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.304302777255476e-05, + "loss": 3.4522, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.303464182504424e-05, + "loss": 3.4547, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3026272256337452e-05, + "loss": 3.451, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.301788630882693e-05, + "loss": 3.454, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3009500361316412e-05, + "loss": 3.4525, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3001114413805892e-05, + "loss": 3.4443, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.2992744845099105e-05, + "loss": 3.4547, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.298435889758858e-05, + "loss": 3.453, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.297597295007806e-05, + "loss": 3.4665, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.296758700256754e-05, + "loss": 3.4655, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2959217433860754e-05, + "loss": 3.4574, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2950831486350234e-05, + "loss": 3.4483, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2942445538839713e-05, + "loss": 3.4577, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2934059591329193e-05, + "loss": 3.4571, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2925690022622403e-05, + "loss": 3.4633, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.2917304075111882e-05, + "loss": 3.4555, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908918127601366e-05, + "loss": 3.4471, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900532180090846e-05, + "loss": 3.4602, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2892162611384055e-05, + "loss": 3.4583, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883776663873535e-05, + "loss": 3.4516, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2875390716363015e-05, + "loss": 3.455, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.2867004768852495e-05, + "loss": 3.4514, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2858635200145707e-05, + "loss": 3.4456, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2850249252635187e-05, + "loss": 3.4396, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2841863305124667e-05, + "loss": 3.4556, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2833477357614147e-05, + "loss": 3.4521, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2825107788907356e-05, + "loss": 3.4502, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.2816721841396836e-05, + "loss": 3.4502, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.280833589388632e-05, + "loss": 3.4469, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.27999499463758e-05, + "loss": 3.4664, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.279158037766901e-05, + "loss": 3.4699, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.278319443015849e-05, + "loss": 3.4599, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.277480848264797e-05, + "loss": 3.4606, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.276642253513745e-05, + "loss": 3.4464, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.275805296643066e-05, + "loss": 3.4493, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.274966701892014e-05, + "loss": 3.4444, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.274128107140962e-05, + "loss": 3.4477, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.27328951238991e-05, + "loss": 3.4531, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.272452555519231e-05, + "loss": 3.4556, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.271613960768179e-05, + "loss": 3.455, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707753660171273e-05, + "loss": 3.4533, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2699367712660753e-05, + "loss": 3.4542, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2690998143953962e-05, + "loss": 3.4501, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.2682612196443442e-05, + "loss": 3.4551, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2674226248932922e-05, + "loss": 3.4561, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665840301422402e-05, + "loss": 3.4644, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2657470732715615e-05, + "loss": 3.4635, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2649084785205095e-05, + "loss": 3.4536, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2640698837694574e-05, + "loss": 3.4593, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2632312890184054e-05, + "loss": 3.4498, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.2623943321477264e-05, + "loss": 3.4629, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2615557373966743e-05, + "loss": 3.4547, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2607171426456223e-05, + "loss": 3.4545, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598785478945707e-05, + "loss": 3.4506, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2590415910238916e-05, + "loss": 3.4615, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.2582029962728396e-05, + "loss": 3.451, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.2573644015217876e-05, + "loss": 3.4554, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.2565258067707352e-05, + "loss": 3.4532, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.2556888499000568e-05, + "loss": 3.4543, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2548502551490048e-05, + "loss": 3.4588, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2540116603979528e-05, + "loss": 3.458, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531730656469005e-05, + "loss": 3.4611, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2523361087762217e-05, + "loss": 3.4463, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.2514975140251697e-05, + "loss": 3.4517, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.852844715118408, + "eval_runtime": 309.1043, + "eval_samples_per_second": 1234.506, + "eval_steps_per_second": 38.579, + "step": 1679030 + }, + { + "epoch": 0.0, + "learning_rate": 2.2506589192741177e-05, + "loss": 3.4487, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2498203245230657e-05, + "loss": 3.4461, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2489817297720137e-05, + "loss": 3.4593, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2481431350209617e-05, + "loss": 3.4552, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2473061781502826e-05, + "loss": 3.4627, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464675833992306e-05, + "loss": 3.4504, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.245628988648179e-05, + "loss": 3.4475, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244790393897127e-05, + "loss": 3.4479, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243953437026448e-05, + "loss": 3.4507, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.243114842275396e-05, + "loss": 3.4485, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.242276247524344e-05, + "loss": 3.4575, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2414376527732918e-05, + "loss": 3.4621, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2406023337829863e-05, + "loss": 3.4365, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2397637390319343e-05, + "loss": 3.4442, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2389251442808823e-05, + "loss": 3.4541, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.23808654952983e-05, + "loss": 3.438, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.237247954778778e-05, + "loss": 3.4463, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.236409360027726e-05, + "loss": 3.4495, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355707652766743e-05, + "loss": 3.4465, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2347321705256223e-05, + "loss": 3.4651, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338952136549432e-05, + "loss": 3.451, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2330566189038912e-05, + "loss": 3.4515, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2322180241528392e-05, + "loss": 3.4492, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313794294017872e-05, + "loss": 3.4548, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2305424725311084e-05, + "loss": 3.4494, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2297038777800564e-05, + "loss": 3.4502, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2288652830290044e-05, + "loss": 3.4444, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2280266882779524e-05, + "loss": 3.4392, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2271897314072733e-05, + "loss": 3.4482, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2263511366562213e-05, + "loss": 3.4443, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2255125419051697e-05, + "loss": 3.4513, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246755850344906e-05, + "loss": 3.4497, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2238369902834386e-05, + "loss": 3.4547, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2229983955323866e-05, + "loss": 3.4579, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2221598007813346e-05, + "loss": 3.4451, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2213228439106558e-05, + "loss": 3.4525, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2204842491596038e-05, + "loss": 3.449, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2196456544085518e-05, + "loss": 3.4459, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2188070596574998e-05, + "loss": 3.4358, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179701027868207e-05, + "loss": 3.4422, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2171315080357687e-05, + "loss": 3.4423, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2162929132847167e-05, + "loss": 3.452, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2154543185336647e-05, + "loss": 3.447, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.214617361662986e-05, + "loss": 3.4466, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.213778766911934e-05, + "loss": 3.4654, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.212940172160882e-05, + "loss": 3.448, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.21210157740983e-05, + "loss": 3.4493, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.211264620539151e-05, + "loss": 3.4416, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2104260257880992e-05, + "loss": 3.4333, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2095874310370472e-05, + "loss": 3.4605, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.208748836285995e-05, + "loss": 3.4456, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.207911879415316e-05, + "loss": 3.4418, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.207073284664264e-05, + "loss": 3.4453, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.206234689913212e-05, + "loss": 3.4473, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.20539609516216e-05, + "loss": 3.4236, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2045591382914813e-05, + "loss": 3.4471, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2037205435404293e-05, + "loss": 3.4413, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028819487893773e-05, + "loss": 3.4384, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.202043354038325e-05, + "loss": 3.4551, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2012063971676462e-05, + "loss": 3.4415, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003678024165945e-05, + "loss": 3.4437, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1995292076655425e-05, + "loss": 3.4509, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986906129144902e-05, + "loss": 3.4369, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1978536560438114e-05, + "loss": 3.4362, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1970150612927594e-05, + "loss": 3.441, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961764665417074e-05, + "loss": 3.4428, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1953378717906554e-05, + "loss": 3.4414, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1945009149199767e-05, + "loss": 3.4369, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936623201689247e-05, + "loss": 3.43, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1928237254178723e-05, + "loss": 3.4381, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.1919851306668203e-05, + "loss": 3.456, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.1911481737961416e-05, + "loss": 3.4401, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.19030957904509e-05, + "loss": 3.4582, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894709842940376e-05, + "loss": 3.4524, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1886323895429856e-05, + "loss": 3.4459, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877954326723068e-05, + "loss": 3.4391, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1869568379212545e-05, + "loss": 3.457, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1861182431702028e-05, + "loss": 3.4431, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1852796484191508e-05, + "loss": 3.4363, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.184442691548472e-05, + "loss": 3.4559, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1836040967974197e-05, + "loss": 3.4471, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827655020463677e-05, + "loss": 3.4512, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1819269072953157e-05, + "loss": 3.4439, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.181089950424637e-05, + "loss": 3.4303, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.180251355673585e-05, + "loss": 3.432, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179412760922533e-05, + "loss": 3.4394, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.178574166171481e-05, + "loss": 3.4448, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.177737209300802e-05, + "loss": 3.4441, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.17689861454975e-05, + "loss": 3.4387, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.176060019798698e-05, + "loss": 3.4429, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.175221425047646e-05, + "loss": 3.4325, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.174384468176967e-05, + "loss": 3.4414, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173545873425915e-05, + "loss": 3.4407, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.172707278674863e-05, + "loss": 3.4573, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.171868683923811e-05, + "loss": 3.4562, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1710317270531323e-05, + "loss": 3.4468, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701931323020803e-05, + "loss": 3.4392, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693545375510283e-05, + "loss": 3.4482, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1685159427999763e-05, + "loss": 3.4402, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1676789859292972e-05, + "loss": 3.4541, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1668403911782452e-05, + "loss": 3.4426, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1660017964271932e-05, + "loss": 3.4395, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651632016761415e-05, + "loss": 3.4457, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1643262448054624e-05, + "loss": 3.451, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634876500544104e-05, + "loss": 3.436, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1626490553033584e-05, + "loss": 3.444, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1618104605523064e-05, + "loss": 3.4364, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1609735036816277e-05, + "loss": 3.437, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1601349089305757e-05, + "loss": 3.4259, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592963141795237e-05, + "loss": 3.4474, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584593573088446e-05, + "loss": 3.4397, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1576207625577926e-05, + "loss": 3.4392, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1567821678067406e-05, + "loss": 3.4415, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1559435730556886e-05, + "loss": 3.4361, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.1551066161850098e-05, + "loss": 3.4514, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1542680214339578e-05, + "loss": 3.4604, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1534294266829058e-05, + "loss": 3.4491, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525908319318538e-05, + "loss": 3.4499, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517538750611747e-05, + "loss": 3.4378, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.150915280310123e-05, + "loss": 3.4395, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.150076685559071e-05, + "loss": 3.4306, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.149238090808019e-05, + "loss": 3.4412, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.14840113393734e-05, + "loss": 3.4392, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.147562539186288e-05, + "loss": 3.4431, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.146723944435236e-05, + "loss": 3.4456, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.145885349684184e-05, + "loss": 3.4408, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1450483928135052e-05, + "loss": 3.4491, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.1442097980624532e-05, + "loss": 3.4356, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1433712033114012e-05, + "loss": 3.4451, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.142532608560349e-05, + "loss": 3.441, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.14169565168967e-05, + "loss": 3.4504, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1408570569386184e-05, + "loss": 3.4516, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1400184621875664e-05, + "loss": 3.4437, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1391798674365144e-05, + "loss": 3.4482, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1383429105658353e-05, + "loss": 3.4409, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1375043158147833e-05, + "loss": 3.4488, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1366657210637313e-05, + "loss": 3.4438, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1358271263126793e-05, + "loss": 3.4466, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349901694420005e-05, + "loss": 3.4374, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1341515746909485e-05, + "loss": 3.4492, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1333129799398965e-05, + "loss": 3.4385, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1324743851888445e-05, + "loss": 3.4435, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1316374283181654e-05, + "loss": 3.4429, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307988335671138e-05, + "loss": 3.4448, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299602388160618e-05, + "loss": 3.4452, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1291216440650094e-05, + "loss": 3.4455, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282846871943307e-05, + "loss": 3.4523, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1274460924432787e-05, + "loss": 3.433, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1266074976922267e-05, + "loss": 3.4472, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.85307240486145, + "eval_runtime": 308.8852, + "eval_samples_per_second": 1235.381, + "eval_steps_per_second": 38.607, + "step": 1755350 + }, + { + "epoch": 1.0, + "learning_rate": 2.1257689029411747e-05, + "loss": 3.4398, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.124931946070496e-05, + "loss": 3.434, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.124093351319444e-05, + "loss": 3.4473, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.123254756568392e-05, + "loss": 3.4431, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.1224161618173396e-05, + "loss": 3.451, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.1215792049466608e-05, + "loss": 3.4405, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.120740610195609e-05, + "loss": 3.4385, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.1199020154445568e-05, + "loss": 3.4364, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.1190634206935048e-05, + "loss": 3.442, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.118226463822826e-05, + "loss": 3.4326, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.117387869071774e-05, + "loss": 3.4476, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.1165492743207217e-05, + "loss": 3.4467, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.1157123174500433e-05, + "loss": 3.4338, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.1148737226989913e-05, + "loss": 3.4278, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.114035127947939e-05, + "loss": 3.4409, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.113196533196887e-05, + "loss": 3.4292, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.112357938445835e-05, + "loss": 3.4369, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.111519343694783e-05, + "loss": 3.4363, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.110680748943731e-05, + "loss": 3.4378, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.1098421541926793e-05, + "loss": 3.4524, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.109005197322e-05, + "loss": 3.4432, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.108166602570948e-05, + "loss": 3.4357, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.107328007819896e-05, + "loss": 3.4379, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.106489413068844e-05, + "loss": 3.4437, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1056524561981654e-05, + "loss": 3.4332, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1048138614471134e-05, + "loss": 3.4449, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1039752666960614e-05, + "loss": 3.4349, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.1031366719450094e-05, + "loss": 3.4295, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.1022997150743303e-05, + "loss": 3.4352, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.1014611203232783e-05, + "loss": 3.4402, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1006225255722263e-05, + "loss": 3.4373, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0997839308211746e-05, + "loss": 3.4413, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0989469739504955e-05, + "loss": 3.446, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.0981083791994435e-05, + "loss": 3.4483, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.0972697844483915e-05, + "loss": 3.4307, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0964328275777124e-05, + "loss": 3.4426, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0955942328266608e-05, + "loss": 3.4424, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0947556380756088e-05, + "loss": 3.4322, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0939170433245568e-05, + "loss": 3.425, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0930800864538777e-05, + "loss": 3.4294, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.0922414917028257e-05, + "loss": 3.4348, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0914028969517737e-05, + "loss": 3.4427, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0905643022007217e-05, + "loss": 3.4315, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.089727345330043e-05, + "loss": 3.4336, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.088888750578991e-05, + "loss": 3.4522, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.088050155827939e-05, + "loss": 3.4408, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.087211561076887e-05, + "loss": 3.4401, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.0863746042062078e-05, + "loss": 3.4295, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.085536009455156e-05, + "loss": 3.4211, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.084697414704104e-05, + "loss": 3.4499, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.0838588199530518e-05, + "loss": 3.433, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.083021863082373e-05, + "loss": 3.4327, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.082183268331321e-05, + "loss": 3.4393, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.081344673580269e-05, + "loss": 3.4317, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.080506078829217e-05, + "loss": 3.4179, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.0796691219585383e-05, + "loss": 3.4319, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.0788305272074863e-05, + "loss": 3.4325, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.0779919324564343e-05, + "loss": 3.4314, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.077153337705382e-05, + "loss": 3.4416, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.076316380834703e-05, + "loss": 3.4322, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.0754777860836515e-05, + "loss": 3.4308, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.074639191332599e-05, + "loss": 3.4412, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.073800596581547e-05, + "loss": 3.422, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.0729636397108684e-05, + "loss": 3.428, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.0721250449598164e-05, + "loss": 3.4304, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.071286450208764e-05, + "loss": 3.4282, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0704478554577124e-05, + "loss": 3.426, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0696108985870336e-05, + "loss": 3.429, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0687723038359816e-05, + "loss": 3.4178, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.0679337090849293e-05, + "loss": 3.4256, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.0670951143338773e-05, + "loss": 3.4446, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0662581574631985e-05, + "loss": 3.4255, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0654195627121465e-05, + "loss": 3.45, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0645809679610945e-05, + "loss": 3.4388, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0637423732100425e-05, + "loss": 3.4396, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.0629054163393638e-05, + "loss": 3.4278, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.0620668215883114e-05, + "loss": 3.4401, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.0612282268372594e-05, + "loss": 3.4345, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0603896320862078e-05, + "loss": 3.4236, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.059552675215529e-05, + "loss": 3.448, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0587140804644767e-05, + "loss": 3.4353, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0578754857134247e-05, + "loss": 3.4378, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.0570368909623726e-05, + "loss": 3.4388, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.056199934091694e-05, + "loss": 3.4167, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.055361339340642e-05, + "loss": 3.4192, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.05452274458959e-05, + "loss": 3.4258, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.053684149838538e-05, + "loss": 3.4353, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0528471929678588e-05, + "loss": 3.4335, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0520085982168068e-05, + "loss": 3.4299, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.0511700034657548e-05, + "loss": 3.4302, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.050331408714703e-05, + "loss": 3.4234, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.049494451844024e-05, + "loss": 3.429, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.048655857092972e-05, + "loss": 3.428, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.04781726234192e-05, + "loss": 3.4446, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.046978667590868e-05, + "loss": 3.4506, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0461417107201893e-05, + "loss": 3.4309, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0453031159691373e-05, + "loss": 3.427, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.0444645212180853e-05, + "loss": 3.4377, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.0436259264670332e-05, + "loss": 3.4314, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.042788969596354e-05, + "loss": 3.4409, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.041950374845302e-05, + "loss": 3.4319, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.04111178009425e-05, + "loss": 3.4298, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.0402731853431985e-05, + "loss": 3.4337, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.0394362284725194e-05, + "loss": 3.4388, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.0385976337214674e-05, + "loss": 3.4255, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.0377590389704154e-05, + "loss": 3.432, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.0369204442193634e-05, + "loss": 3.4287, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.0360834873486846e-05, + "loss": 3.4243, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0352448925976326e-05, + "loss": 3.4212, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.0344062978465806e-05, + "loss": 3.4319, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0335677030955286e-05, + "loss": 3.4327, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.0327307462248495e-05, + "loss": 3.4233, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.0318921514737975e-05, + "loss": 3.4331, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.0310535567227455e-05, + "loss": 3.4274, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.030214961971694e-05, + "loss": 3.4385, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0293780051010148e-05, + "loss": 3.4462, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.0285394103499628e-05, + "loss": 3.4368, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.0277008155989108e-05, + "loss": 3.4388, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.0268622208478587e-05, + "loss": 3.4239, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.02602526397718e-05, + "loss": 3.4317, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.025186669226128e-05, + "loss": 3.4205, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.024348074475076e-05, + "loss": 3.4276, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.023509479724024e-05, + "loss": 3.4301, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.022672522853345e-05, + "loss": 3.4313, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.021833928102293e-05, + "loss": 3.4309, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.020995333351241e-05, + "loss": 3.4315, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.020156738600189e-05, + "loss": 3.4399, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.01931978172951e-05, + "loss": 3.4279, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.018481186978458e-05, + "loss": 3.4319, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.017642592227406e-05, + "loss": 3.4337, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0168039974763538e-05, + "loss": 3.4379, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.0159670406056754e-05, + "loss": 3.4438, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.0151284458546234e-05, + "loss": 3.4318, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.0142898511035714e-05, + "loss": 3.4365, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.013451256352519e-05, + "loss": 3.4285, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0126142994818403e-05, + "loss": 3.4395, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0117757047307883e-05, + "loss": 3.4284, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0109371099797363e-05, + "loss": 3.4345, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0100985152286842e-05, + "loss": 3.4285, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0092615583580055e-05, + "loss": 3.4427, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0084229636069535e-05, + "loss": 3.4261, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.007584368855901e-05, + "loss": 3.4331, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.006745774104849e-05, + "loss": 3.4343, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.0059088172341707e-05, + "loss": 3.435, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0050702224831187e-05, + "loss": 3.4315, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0042316277320664e-05, + "loss": 3.4335, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.0033930329810144e-05, + "loss": 3.4409, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.0025560761103356e-05, + "loss": 3.4213, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.0017174813592833e-05, + "loss": 3.4383, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.8561525344848633, + "eval_runtime": 308.1771, + "eval_samples_per_second": 1238.22, + "eval_steps_per_second": 38.695, + "step": 1831670 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.2742391509820744e+18, + "trial_name": null, + "trial_params": null +}